© 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. 56411
    Prev
    Next
    INDEX
    Explanations

    keywords that indicate customer engagement and service quality

    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
    zin
    -0.06
    chwitz
    -0.06
    ÑĢÑĥÑĤ
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
    actions
    -0.06
    ç´
    -0.06
    iser
    -0.06
    atu
    -0.05
    ç¢
    -0.05
    éī
    -0.05
    POSITIVE LOGITS
    SELL
    0.06
    burse
    0.06
    itive
    0.06
    ereotype
    0.06
    -urlencoded
    0.06
    ieval
    0.06
    _html
    0.06
    ÑĢоÑģÑĤо
    0.06
    illisecond
    0.06
    ICLES
    0.06
    Activations Density 0.042%

    No Known Activations