© 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. 63273
    Prev
    Next
    INDEX
    Explanations

    numerical values and punctuation that signify conclusions or significant statements

    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
    oster
    -0.07
    alc
    -0.07
    endor
    -0.07
    kün
    -0.07
     techn
    -0.07
     dün
    -0.06
    zas
    -0.06
    lemen
    -0.06
    .opensource
    -0.06
    odie
    -0.06
    POSITIVE LOGITS
     GOODMAN
    0.07
    inet
    0.06
    pf
    0.06
    needed
    0.06
    주
    0.06
    funcs
    0.06
    Fmt
    0.06
    å·
    0.06
    major
    0.05
    ?(:
    0.05
    Activations Density 0.000%

    No Known Activations