© 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. 41699
    Prev
    Next
    INDEX
    Explanations

    positive evaluations of media content

    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
    éĢĶ
    -0.07
    .Guna
    -0.07
    itemap
    -0.06
    лива
    -0.06
     Huck
    -0.06
    PrototypeOf
    -0.06
    ounty
    -0.06
    rupa
    -0.06
    \Html
    -0.06
    /***************************************************************************↵
    -0.06
    POSITIVE LOGITS
    ë¬
    0.07
    icz
    0.06
     Zimmer
    0.06
    ä¹ĭä¸Ģ
    0.06
    runtime
    0.05
     Polit
    0.05
    OID
    0.05
    prox
    0.05
    master
    0.05
    rell
    0.05
    Activations Density 0.001%

    No Known Activations