© 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. 39476
    Prev
    Next
    INDEX
    Explanations

    phrases indicating alternatives or options

    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
     gard
    -0.07
    historic
    -0.06
    ÏĦÏģο
    -0.06
    lices
    -0.06
    umblr
    -0.06
    front
    -0.06
    ikipedia
    -0.06
     ãĥĽ
    -0.06
    enci
    -0.06
    TR
    -0.06
    POSITIVE LOGITS
    ancode
    0.08
    lum
    0.07
    zik
    0.07
    intree
    0.07
    (clicked
    0.06
    ìŀIJìĿ¸
    0.06
     تÛĮ
    0.06
    .cl
    0.06
    Squared
    0.06
     §§
    0.06
    Activations Density 0.003%

    No Known Activations