© 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. 95882
    Prev
    Next
    INDEX
    Explanations

    references to government officials and statements

    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
    ãĥ³ãĥĦ
    -0.07
     zmÄĽny
    -0.07
    _months
    -0.07
    peat
    -0.07
    eros
    -0.07
    guarded
    -0.07
     Months
    -0.07
    jeme
    -0.07
    olut
    -0.07
     SqlParameter
    -0.07
    POSITIVE LOGITS
     emergency
    0.07
     immediate
    0.07
     Immediate
    0.07
     immediately
    0.07
    yal
    0.07
     Emergency
    0.06
     hourly
    0.06
     disaster
    0.06
     hour
    0.06
    ÚĨÛĮ
    0.06
    Activations Density 0.011%

    No Known Activations