© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128675
    Prev
    Next
    INDEX
    Explanations

    references to people, particularly those with notable contributions or positions

    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
    šky
    -0.08
    sterol
    -0.08
    hip
    -0.08
    šku
    -0.07
    phinx
    -0.07
    stown
    -0.07
    ÃľM
    -0.06
    iac
    -0.06
    elles
    -0.06
    upo
    -0.06
    POSITIVE LOGITS
    mpp
    0.06
    adil
    0.06
    aille
    0.06
    icode
    0.06
     vice
    0.06
    -thumbnails
    0.06
    æ´ŀ
    0.06
    -placeholder
    0.06
     scrut
    0.06
    ">\
    0.06
    Activations Density 0.018%

    No Known Activations