© 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. 124564
    Prev
    Next
    INDEX
    Explanations

    noteworthy accomplishments and recognition of individuals

    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
    quito
    -0.07
    ylon
    -0.07
    IMS
    -0.06
    Ë
    -0.06
    inkel
    -0.06
     NSUInteger
    -0.06
    iseum
    -0.06
    ymoon
    -0.06
    klad
    -0.06
    zik
    -0.06
    POSITIVE LOGITS
    rani
    0.07
     she
    0.07
    hest
    0.06
    æģµ
    0.06
    Ú¯ÛĮ
    0.06
     maternal
    0.06
    ır
    0.06
    evenodd
    0.06
     Tune
    0.06
     multiplied
    0.06
    Activations Density 0.022%

    No Known Activations