© 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. 77395
    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
    erras
    -0.07
    iani
    -0.07
    zend
    -0.07
    ferred
    -0.06
    erd
    -0.06
    eros
    -0.06
    ion
    -0.06
    awah
    -0.06
    posables
    -0.06
    ogl
    -0.06
    POSITIVE LOGITS
    ÑĢоÑĩ
    0.07
     Walsh
    0.06
     guten
    0.06
     Bray
    0.06
    ago
    0.06
    kker
    0.06
     oneself
    0.06
    umba
    0.06
    ÑĤин
    0.06
    bite
    0.06
    Activations Density 0.057%

    No Known Activations