© 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. 87822
    Prev
    Next
    INDEX
    Explanations

    subjects and individuals involved in actions or events

    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
    ediÄŁi
    -0.07
    llib
    -0.07
    ůž
    -0.06
    asal
    -0.06
    .stamp
    -0.06
    _Struct
    -0.06
    ãĥ³ãĤº
    -0.06
    ãĢģäºĮ
    -0.06
    ä¸ĬçļĦ
    -0.06
     erle
    -0.06
    POSITIVE LOGITS
     might
    0.10
    might
    0.08
     likely
    0.08
    LIKELY
    0.07
     should
    0.07
    NA
    0.07
     already
    0.07
    asInstanceOf
    0.07
     would
    0.07
     requested
    0.07
    Activations Density 0.037%

    No Known Activations