© 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. 72066
    Prev
    Next
    INDEX
    Explanations

    references to articles and submissions for publication

    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
     Stra
    -0.07
    ilter
    -0.07
    768
    -0.07
    oph
    -0.06
    лей
    -0.06
    Ïĥε
    -0.06
    ine
    -0.06
    ayer
    -0.06
     Yüz
    -0.06
    krom
    -0.06
    POSITIVE LOGITS
    稿
    0.08
     article
    0.07
     ghost
    0.06
     Traffic
    0.06
     proposed
    0.06
     contributor
    0.06
     contribution
    0.06
    ghost
    0.06
    caffe
    0.06
    eco
    0.06
    Activations Density 0.010%

    No Known Activations