© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123612
    Prev
    Next
    INDEX
    Explanations

    terms indicating inclusion or provision of content or features

    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
     nhau
    -0.07
    ediator
    -0.07
    á»ģn
    -0.07
    erule
    -0.07
     (::
    -0.07
    [".
    -0.07
     СÑĤÑĢана
    -0.07
    áct
    -0.07
    aña
    -0.07
    ẩn
    -0.07
    POSITIVE LOGITS
    oret
    0.08
    oretical
    0.07
     numberWith
    0.07
    illa
    0.07
    orem
    0.06
    semble
    0.06
    ̣
    0.06
     Excell
    0.06
    /re
    0.06
    egr
    0.06
    Activations Density 0.051%

    No Known Activations