© 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. 74915
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or possibility

    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
    vere
    -0.07
    utin
    -0.07
    eyJ
    -0.07
    omik
    -0.07
    ÏĦικο
    -0.07
    ť
    -0.07
    omo
    -0.07
    ´
    -0.07
     Heller
    -0.07
    vn
    -0.07
    POSITIVE LOGITS
     someone
    0.09
     anyone
    0.08
     you
    0.08
     we
    0.07
    áp
    0.07
     people
    0.07
     everyone
    0.06
     somebody
    0.06
    /how
    0.06
    oland
    0.06
    Activations Density 0.006%

    No Known Activations