© 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. 83143
    Prev
    Next
    INDEX
    Explanations

    terms related to correspondence or association 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
    aren
    -0.07
    zens
    -0.07
    /ss
    -0.06
    are
    -0.06
    uffy
    -0.06
    sel
    -0.06
    isle
    -0.06
    ven
    -0.06
    ych
    -0.06
    ila
    -0.06
    POSITIVE LOGITS
    ily
    0.07
    ly
    0.07
    LY
    0.07
    pair
    0.07
    /generated
    0.07
     bitte
    0.07
    iating
    0.07
    ment
    0.07
    rieved
    0.07
    -issue
    0.06
    Activations Density 0.016%

    No Known Activations