© 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 EvalsExportsAPI 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. 61031
    Prev
    Next
    INDEX
    Explanations

    references to restaurants

    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
    quer
    -0.07
    cut
    -0.07
    andy
    -0.06
    hang
    -0.06
    »
    -0.06
    .UIManager
    -0.06
    ULE
    -0.06
    vr
    -0.06
    adem
    -0.06
    vl
    -0.06
    POSITIVE LOGITS
    /bar
    0.10
    ulumi
    0.09
    -grade
    0.08
    _chain
    0.08
    /pub
    0.08
    /movie
    0.08
     chains
    0.08
    -bars
    0.08
    ettes
    0.07
    ofs
    0.07
    Activations Density 0.009%

    No Known Activations