© 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. 9-LLAMASCOPE-RES-131K
    11. 99117
    Prev
    Next
    INDEX
    Explanations

    terms related to biological similarities and analyses in proteins

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    .jasper
    -0.07
    ONTAL
    -0.07
    #index
    -0.07
    ambre
    -0.07
    ober
    -0.07
    \Event
    -0.06
     ance
    -0.06
    istrat
    -0.06
    imei
    -0.06
    AndView
    -0.06
    POSITIVE LOGITS
    _
    0.06
    atha
    0.06
    åºĦ
    0.06
    रण
    0.06
     кл
    0.05
    rief
    0.05
    oog
    0.05
    lossen
    0.05
     simil
    0.05
     mould
    0.05
    Activations Density 0.004%

    No Known Activations