© 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. 76328
    Prev
    Next
    INDEX
    Explanations

    numeric values related to limits and constraints in mathematical or algorithmic 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
     splitted
    -0.07
     Howe
    -0.07
    omik
    -0.07
    ýt
    -0.06
     Dün
    -0.06
    âh
    -0.06
    rosso
    -0.06
     mute
    -0.06
    ØŃص
    -0.06
    imli
    -0.06
    POSITIVE LOGITS
     ("
    0.07
    æĹı
    0.06
     NB
    0.06
    aji
    0.06
    -unused
    0.06
    ormap
    0.06
     embar
    0.06
    isha
    0.06
    ÑĢÑı
    0.06
    лаÑĩ
    0.05
    Activations Density 0.000%

    No Known Activations