© 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. 4865
    Prev
    Next
    INDEX
    Explanations

    references to individuals and specific actions or occurrences related to them

    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
    okino
    -0.08
    mos
    -0.07
    ouro
    -0.07
    ullan
    -0.07
    اÙĪر
    -0.06
    idor
    -0.06
    ULO
    -0.06
     KE
    -0.06
     tolik
    -0.06
    oco
    -0.06
    POSITIVE LOGITS
     available
    0.09
     encountered
    0.09
    available
    0.08
     sight
    0.08
    ailable
    0.07
    Available
    0.07
    -available
    0.07
    _available
    0.07
     Available
    0.07
     found
    0.07
    Activations Density 0.028%

    No Known Activations