© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 10551
    Prev
    Next
    INDEX
    Explanations

    words indicating the level of importance or significant involvement in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "play an active role" or variations of "important/significant/decisive role".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»Ļi
    -0.15
    alian
    -0.15
    ongan
    -0.15
    .tp
    -0.15
    #ac
    -0.14
    anco
    -0.14
    ometr
    -0.14
    _pb
    -0.14
    upert
    -0.14
    /validation
    -0.14
    POSITIVE LOGITS
    angelo
    0.14
    usra
    0.14
     role
    0.14
    ZZ
    0.14
     Rif
    0.14
    Configurer
    0.14
    ibri
    0.14
     Kling
    0.13
     shadow
    0.13
     roles
    0.13
    Activations Density 0.198%

    No Known Activations