© 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. 15-LLAMASCOPE-RES-131K
    11. 26874
    Prev
    Next
    INDEX
    Explanations

    terms related to events and competitions

    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
     lack
    -0.06
     [
    -0.06
    aku
    -0.06
     either
    -0.06
     since
    -0.06
    oks
    -0.06
     considering
    -0.06
     oo
    -0.06
     Calder
    -0.05
     mult
    -0.05
    POSITIVE LOGITS
    enstein
    0.07
    pcf
    0.07
     nên
    0.07
    ä¸Ķ
    0.07
    CJK
    0.07
    ëĦIJ
    0.07
    )did
    0.07
    ieri
    0.06
    ationship
    0.06
    umbn
    0.06
    Activations Density 0.030%

    No Known Activations