Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 78483
    Prev
    Next
    INDEX
    Explanations

    instances of numeric values and their contextual significance

    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
    ãĥ³ãĤ¬
    -0.07
    hub
    -0.06
    mani
    -0.06
    );\↵
    -0.06
    asted
    -0.06
    abant
    -0.06
    ле
    -0.05
    ook
    -0.05
    illi
    -0.05
     Trem
    -0.05
    POSITIVE LOGITS
    à¸ĵà¸ij
    0.07
    ÷
    0.07
    unca
    0.07
    Vtbl
    0.07
    otime
    0.07
     mechan
    0.07
    MemoryWarning
    0.06
    _integration
    0.06
     addCriterion
    0.06
    ikal
    0.06
    Activations Density 0.000%

    No Known Activations