© 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. 108659
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting planning or organization for activities

    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
     Plain
    -0.07
     plain
    -0.06
    abilia
    -0.06
    áž
    -0.06
    á»įng
    -0.06
    isay
    -0.06
    aptive
    -0.06
    -INF
    -0.06
     closures
    -0.06
     meiden
    -0.06
    POSITIVE LOGITS
    åŃĿ
    0.07
    ez
    0.07
    achten
    0.07
     Ark
    0.06
    599
    0.06
    245
    0.06
    ละ
    0.06
    akat
    0.06
     pitch
    0.06
    457
    0.06
    Activations Density 0.026%

    No Known Activations