© 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. 17-LLAMASCOPE-RES-131K
    11. 126289
    Prev
    Next
    INDEX
    Explanations

    components related to significant subjects or entities in various contexts

    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
    allery
    -0.07
    STR
    -0.06
    227
    -0.06
    omba
    -0.06
    XM
    -0.06
    worm
    -0.06
    iani
    -0.06
    026
    -0.06
    arsi
    -0.06
    stro
    -0.05
    POSITIVE LOGITS
    atel
    0.07
    ihan
    0.07
    utc
    0.06
    154
    0.06
    Transpose
    0.06
    antic
    0.06
    ispers
    0.06
     unary
    0.06
    OTES
    0.06
    urv
    0.06
    Activations Density 0.001%

    No Known Activations