© 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. 17-LLAMASCOPE-RES-131K
    11. 2249
    Prev
    Next
    INDEX
    Explanations

    references to reviews and review-related content

    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
    380
    -0.07
    keiten
    -0.06
    lide
    -0.06
    foot
    -0.06
    etal
    -0.06
    .MODE
    -0.06
    _PROGRAM
    -0.06
    обав
    -0.06
     Alto
    -0.06
     kvin
    -0.06
    POSITIVE LOGITS
    ¤¤
    0.07
    Obsolete
    0.07
    issy
    0.06
    /comments
    0.06
    éĢļãĤĬ
    0.06
    /report
    0.06
    -rating
    0.06
    afx
    0.06
    FirstChild
    0.06
    Ïħγ
    0.06
    Activations Density 0.012%

    No Known Activations