© 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. 5-LLAMASCOPE-RES-131K
    11. 126056
    Prev
    Next
    INDEX
    Explanations

    programming-related declarations and definitions

    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
    ean
    -0.06
    elan
    -0.06
    uen
    -0.06
    ipp
    -0.06
    ric
    -0.06
    emic
    -0.06
    elen
    -0.06
    Occurred
    -0.06
    emi
    -0.06
    ern
    -0.06
    POSITIVE LOGITS
     münchen
    0.06
    ispens
    0.06
    fault
    0.06
    ffa
    0.06
    Increment
    0.06
    atform
    0.06
    åºŃ
    0.06
    292
    0.06
    QUI
    0.06
    increment
    0.06
    Activations Density 0.001%

    No Known Activations