© 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. 15-LLAMASCOPE-RES-131K
    11. 90105
    Prev
    Next
    INDEX
    Explanations

    instances of receiving or received in various contexts

    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
    reece
    -0.07
    lio
    -0.07
    Ģ
    -0.07
    ret
    -0.06
     ведÑĮ
    -0.06
    ERM
    -0.06
    vel
    -0.06
    REW
    -0.06
    oro
    -0.06
    ertz
    -0.06
    POSITIVE LOGITS
    /send
    0.08
    ç¶Ļ
    0.08
    až
    0.07
    MemoryWarning
    0.07
     porr
    0.07
    OrElse
    0.07
    createFrom
    0.07
    /report
    0.07
    ElementsByTagName
    0.07
    lg
    0.07
    Activations Density 0.030%

    No Known Activations