© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 126072
    Prev
    Next
    INDEX
    Explanations

    occurrences of proper nouns and specific terms related to awards and recognition

    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
    sko
    -0.07
    uo
    -0.07
    ourd
    -0.07
    work
    -0.06
    iveness
    -0.06
    ACHINE
    -0.06
    MMdd
    -0.06
    gres
    -0.06
    isser
    -0.06
    amac
    -0.06
    POSITIVE LOGITS
    shaw
    0.07
    ¼
    0.07
    ERO
    0.07
     Madness
    0.06
     gió
    0.06
     madness
    0.06
    erie
    0.06
    eded
    0.06
    åł
    0.06
    COPE
    0.06
    Activations Density 0.002%

    No Known Activations