© 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. 77082
    Prev
    Next
    INDEX
    Explanations

    mentions of significant actions and decisions related to planning or management

    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
    /**č↵
    -0.07
    ila
    -0.07
    aus
    -0.06
    mani
    -0.06
    uel
    -0.06
    ug
    -0.06
    astically
    -0.06
    lag
    -0.06
    Question
    -0.06
    weeney
    -0.06
    POSITIVE LOGITS
    ă
    0.10
     destinationViewController
    0.08
    imbus
    0.07
    istrovstvÃŃ
    0.07
     ì¶ľìŀ¥
    0.07
    SKU
    0.07
    erah
    0.07
    ditor
    0.07
    addtogroup
    0.07
    ÌĨ
    0.06
    Activations Density 1.298%

    No Known Activations