© 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. 9-LLAMASCOPE-RES-131K
    11. 94625
    Prev
    Next
    INDEX
    Explanations

    terms related to quality and validity

    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
     bare
    -0.06
    аÑĤков
    -0.06
    usz
    -0.06
    us
    -0.06
    gle
    -0.06
     gre
    -0.06
     vez
    -0.06
     bard
    -0.06
    GRE
    -0.06
    gre
    -0.05
    POSITIVE LOGITS
    linky
    0.08
    vyk
    0.08
    inded
    0.07
    ｡
    0.07
    auc
    0.07
     addCriterion
    0.07
    707
    0.07
    illes
    0.07
    _cached
    0.07
    rowsable
    0.07
    Activations Density 0.065%

    No Known Activations