© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 17945
    Prev
    Next
    INDEX
    Explanations

    references to membership, donations, and support for organizations

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

    membership and enrollment

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    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
    riba
    -0.16
    fé
    -0.15
    iego
    -0.15
     primitive
    -0.15
    -Cal
    -0.14
    imitive
    -0.14
    igu
    -0.14
     é©
    -0.14
     Personality
    -0.14
    crete
    -0.14
    POSITIVE LOGITS
    asan
    0.18
     Nec
    0.15
    æĿĤ
    0.14
     Sad
    0.14
    Ñīи
    0.14
    zM
    0.14
    .EventSystems
    0.14
    inis
    0.13
     Bosch
    0.13
     Ir
    0.13
    Activations Density 0.242%

    No Known Activations