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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 74664
    Prev
    Next
    INDEX
    Explanations

    references to dispensaries related to cannabis

    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
    utz
    -0.09
    вен
    -0.07
    lest
    -0.07
    bsolute
    -0.07
    rang
    -0.07
    tdown
    -0.07
    hq
    -0.07
    acey
    -0.07
    /high
    -0.07
    hydr
    -0.07
    POSITIVE LOGITS
    able
    0.08
     dispens
    0.08
    iment
    0.07
    airy
    0.07
    ible
    0.07
    ellan
    0.07
    iron
    0.07
    esc
    0.07
    il
    0.06
    ital
    0.06
    Activations Density 0.009%

    No Known Activations