© 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. 40840
    Prev
    Next
    INDEX
    Explanations

    comparisons between service providers or products

    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
    ubi
    -0.07
    éłĨ
    -0.06
     blame
    -0.06
    leyici
    -0.06
    oret
    -0.06
     erw
    -0.06
    ÏĦαν
    -0.06
    utta
    -0.06
    erli
    -0.06
    arin
    -0.06
    POSITIVE LOGITS
     other
    0.15
     elsewhere
    0.14
     others
    0.13
    other
    0.12
    åħ¶ä»ĸ
    0.11
     дÑĢÑĥгиÑħ
    0.11
     anderen
    0.11
     andere
    0.11
    (other
    0.11
     otros
    0.11
    Activations Density 0.044%

    No Known Activations