© 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 EvalsExportsAPI 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. 57400
    Prev
    Next
    INDEX
    Explanations

    specific names and titles related to various subjects, especially in entertainment and awards

    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
     forth
    -0.07
    jos
    -0.07
    lish
    -0.06
    ITO
    -0.06
    rå
    -0.06
    (strtolower
    -0.06
    jian
    -0.06
    ias
    -0.06
    ISH
    -0.06
    лиÑĤ
    -0.06
    POSITIVE LOGITS
    /Dk
    0.08
    /Peak
    0.08
    dash
    0.07
    deaux
    0.07
     Erotische
    0.07
    Ìģ
    0.07
    /Gate
    0.07
    trap
    0.07
    ï¼ł
    0.07
    odash
    0.07
    Activations Density 0.098%

    No Known Activations