© 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. 125549
    Prev
    Next
    INDEX
    Explanations

    references to positions or coordinates in geometric or programming 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
    Ỽt
    -0.07
    egen
    -0.07
    issan
    -0.06
    _IL
    -0.06
    å±Ĭ
    -0.06
    esti
    -0.06
    ieber
    -0.06
    нила
    -0.06
    ueue
    -0.06
    ingleton
    -0.06
    POSITIVE LOGITS
    ç
    0.07
     доÑĢ
    0.06
    еÑĢв
    0.06
    agr
    0.06
     Barr
    0.06
     Feinstein
    0.06
    ,,,,,,,,
    0.06
    [
    0.06
    xcb
    0.06
    zk
    0.06
    Activations Density 0.040%

    No Known Activations