© 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. 15-LLAMASCOPE-RES-131K
    11. 671
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their relationships to characteristics or classifications

    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
    lex
    -0.07
     cá
    -0.07
    iser
    -0.07
    ising
    -0.06
    lan
    -0.06
    lant
    -0.06
     advoc
    -0.06
    imb
    -0.06
    _override
    -0.06
    ense
    -0.06
    POSITIVE LOGITS
    glob
    0.07
    errat
    0.07
    artment
    0.06
    _INITIALIZER
    0.06
    eron
    0.06
    /cms
    0.06
    gunta
    0.06
    ç±»åŀĭ
    0.06
    pery
    0.06
    (exports
    0.06
    Activations Density 0.075%

    No Known Activations