© 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. 9-LLAMASCOPE-RES-131K
    11. 94345
    Prev
    Next
    INDEX
    Explanations

    references to cancer-related organizations and societies

    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
     bench
    -0.07
     Bench
    -0.07
    .liferay
    -0.07
     thang
    -0.06
    ozor
    -0.06
    anke
    -0.06
    سÙĪب
    -0.06
    _dependency
    -0.06
    .separator
    -0.06
    472
    -0.06
    POSITIVE LOGITS
     Sle
    0.07
    incare
    0.07
     Wahl
    0.06
    rent
    0.06
    enu
    0.06
    mess
    0.06
    indre
    0.06
    aley
    0.06
    bsolute
    0.05
    ultz
    0.05
    Activations Density 0.000%

    No Known Activations