© 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. 26977
    Prev
    Next
    INDEX
    Explanations

    occurrences of URLs within the text

    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
    avage
    -0.06
    warts
    -0.06
    dict
    -0.06
     Jou
    -0.06
    butt
    -0.06
     mercenaries
    -0.06
    jure
    -0.05
    obus
    -0.05
    %E
    -0.05
     Spect
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    bjerg
    0.07
     vX
    0.07
    Wildcard
    0.07
    agoon
    0.07
    keit
    0.07
    eah
    0.07
    ãĤĩãģĨ
    0.07
    anlık
    0.06
    otal
    0.06
    Activations Density 0.000%

    No Known Activations