© 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. 70127
    Prev
    Next
    INDEX
    Explanations

    dates and times mentioned in the document

    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
     воÑĤ
    -0.06
    chez
    -0.06
     completo
    -0.06
    ool
    -0.05
    or
    -0.05
     pointed
    -0.05
    Ãły
    -0.05
    sov
    -0.05
     bumps
    -0.05
    Äįe
    -0.05
    POSITIVE LOGITS
    201
    0.12
    202
    0.09
    iyim
    0.08
    200
    0.08
    199
    0.08
    ajas
    0.07
    roi
    0.07
    ystack
    0.07
    gameObject
    0.07
    eview
    0.07
    Activations Density 0.006%

    No Known Activations