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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 8-LLAMASCOPE-RES-32K
    11. 23065
    Prev
    Next
    INDEX
    Explanations

    words indicating permission, attention, and elements related to human anatomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orent
    -0.19
    arger
    -0.15
    dol
    -0.15
    lang
    -0.15
    pend
    -0.14
     ning
    -0.14
    _CONT
    -0.14
    822
    -0.14
    ONS
    -0.14
    lu
    -0.14
    POSITIVE LOGITS
     Cummings
    0.16
    angstrom
    0.15
    illos
    0.15
    aque
    0.15
    acam
    0.15
    Hierarchy
    0.14
    acas
    0.14
    artner
    0.14
    ompiler
    0.14
     öl
    0.14
    Activations Density 0.018%

    No Known Activations