© 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. 119032
    Prev
    Next
    INDEX
    Explanations

    numerical dates and events in a chronological 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
    panion
    -0.07
    ÑĥÑĢÑĭ
    -0.07
    positories
    -0.07
    ylon
    -0.07
    vider
    -0.07
    [code
    -0.07
    optera
    -0.07
    emonic
    -0.07
    anders
    -0.07
     gridColumn
    -0.07
    POSITIVE LOGITS
    181
    0.07
    zer
    0.07
    isco
    0.07
    191
    0.07
    190
    0.07
    185
    0.06
    183
    0.06
    171
    0.06
    182
    0.06
     romant
    0.06
    Activations Density 0.002%

    No Known Activations