© 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. 679
    Prev
    Next
    INDEX
    Explanations

    alternative options or choices in a context

    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
    Either
    -0.07
     either
    -0.07
    imon
    -0.07
    ãĥ³ãĥģ
    -0.07
     EITHER
    -0.07
    ignon
    -0.07
     Either
    -0.07
    either
    -0.06
    anco
    -0.06
    oven
    -0.06
    POSITIVE LOGITS
     vamp
    0.08
    datatable
    0.07
     Bylo
    0.07
    (æ°´
    0.07
    setProperty
    0.07
    æ³£
    0.06
    _substr
    0.06
    opensource
    0.06
    iteral
    0.06
    }č↵č↵č↵č↵
    0.06
    Activations Density 0.017%

    No Known Activations