© 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. 79403
    Prev
    Next
    INDEX
    Explanations

    instances of highly technical or specialized language

    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
    aqu
    -0.06
    imiter
    -0.06
    chor
    -0.06
    hea
    -0.06
     åĤ
    -0.06
    onta
    -0.06
    alus
    -0.06
    ÑĢеÑħ
    -0.05
    ules
    -0.05
    apia
    -0.05
    POSITIVE LOGITS
    adero
    0.08
    uzey
    0.08
     âĨij
    0.07
    Ľå»º
    0.07
    933
    0.07
    RefCount
    0.07
    ÏįÏĢ
    0.07
    .Focused
    0.06
    RefPtr
    0.06
    ään
    0.06
    Activations Density 0.000%

    No Known Activations