© 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. 79622
    Prev
    Next
    INDEX
    Explanations

    keywords related to entertainment and personal interests

    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
    ocene
    -0.09
    odore
    -0.08
    aceae
    -0.07
    addon
    -0.07
    ocrates
    -0.07
    ogne
    -0.07
    akespeare
    -0.07
    Is
    -0.06
    asley
    -0.06
    ÑĴ
    -0.06
    POSITIVE LOGITS
    ÐłÐĿ
    0.08
    amedi
    0.07
    imdi
    0.07
    çķ
    0.07
    bsite
    0.06
    anship
    0.06
    folio
    0.06
    arLayout
    0.06
    ItemAt
    0.06
    837
    0.06
    Activations Density 0.240%

    No Known Activations