© 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. 57542
    Prev
    Next
    INDEX
    Explanations

    terms associated with user interactions, information handling, and transactions on a web platform

    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
    atore
    -0.07
    ¶Į
    -0.07
    erea
    -0.07
    κι
    -0.06
    shint
    -0.06
    ç©į
    -0.06
    egasus
    -0.06
    iete
    -0.06
    cate
    -0.06
    ulumi
    -0.06
    POSITIVE LOGITS
    ANTI
    0.07
     etc
    0.06
     Strauss
    0.06
    eÄį
    0.06
    compatible
    0.06
     occasion
    0.06
     PMID
    0.06
     dio
    0.06
    Äįen
    0.05
    getSingleton
    0.05
    Activations Density 0.006%

    No Known Activations