© 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. 116463
    Prev
    Next
    INDEX
    Explanations

    references to evaluation and assessment processes

    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
     köln
    -0.07
    iag
    -0.07
     Yardım
    -0.07
    _ratings
    -0.07
    oplevel
    -0.07
    ?action
    -0.07
    åķĬåķĬ
    -0.06
    utom
    -0.06
     addCriterion
    -0.06
     donc
    -0.06
    POSITIVE LOGITS
     any
    0.10
     anything
    0.10
     potential
    0.08
    anything
    0.08
     Any
    0.08
    Any
    0.08
    any
    0.08
    .any
    0.07
     ANY
    0.07
    ä»»ä½ķ
    0.07
    Activations Density 0.026%

    No Known Activations