© 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. 118601
    Prev
    Next
    INDEX
    Explanations

    mentions of headquarters or significant organizational locations

    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
    веÑī
    -0.07
    ply
    -0.07
    alla
    -0.06
     Diablo
    -0.06
     handful
    -0.06
    elp
    -0.06
    oly
    -0.06
    IGH
    -0.06
    uku
    -0.06
    ances
    -0.06
    POSITIVE LOGITS
    quare
    0.08
    ../../../
    0.08
    ilenames
    0.07
    isko
    0.07
    eter
    0.07
    lining
    0.07
    -level
    0.07
    ÚĨÙĩ
    0.07
    eted
    0.07
    /head
    0.07
    Activations Density 0.005%

    No Known Activations