© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 1555
    Prev
    Next
    INDEX
    Explanations

    URLs related to file formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jom
    -0.06
     Watkins
    -0.06
    PG
    -0.06
    rer
    -0.06
     muse
    -0.06
    eve
    -0.06
     wid
    -0.05
    mut
    -0.05
    zeit
    -0.05
    amet
    -0.05
    POSITIVE LOGITS
    decltype
    0.07
    iston
    0.07
    à¤ķन
    0.07
     tô
    0.07
    /java
    0.07
    xda
    0.06
    ิà¸Ĭ
    0.06
    oldur
    0.06
     mái
    0.06
     Nolan
    0.06
    Activations Density 0.000%

    No Known Activations