© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87200
    Prev
    Next
    INDEX
    Explanations

    terms related to entertainment and media

    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
    abet
    -0.06
    stered
    -0.06
    ailable
    -0.06
    .JMenuItem
    -0.06
     Burr
    -0.06
    udit
    -0.06
    ossal
    -0.06
    estival
    -0.06
    ær
    -0.06
    raction
    -0.06
    POSITIVE LOGITS
     tend
    0.09
     generally
    0.08
     typically
    0.07
    kir
    0.07
    akov
    0.07
     tends
    0.07
    usually
    0.07
     usually
    0.07
    uchs
    0.07
    ãģ¥
    0.07
    Activations Density 0.030%

    No Known Activations