© 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. 25-LLAMASCOPE-RES-32K
    11. 20916
    Prev
    Next
    INDEX
    Explanations

    phrases related to terms of service or legal disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urve
    -0.18
    urt
    -0.15
    Ú©Ùħ
    -0.14
    lush
    -0.14
     Leisure
    -0.14
    enou
    -0.14
     bri
    -0.14
     reinterpret
    -0.14
     astr
    -0.13
     Earn
    -0.13
    POSITIVE LOGITS
    AS
    0.23
     AS
    0.21
    ainer
    0.19
     BASIS
    0.18
     basis
    0.16
    osit
    0.16
    _AS
    0.16
    ivos
    0.15
    locator
    0.15
     Cousins
    0.15
    Activations Density 0.004%

    No Known Activations