© 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. 126283
    Prev
    Next
    INDEX
    Explanations

    concepts related to significance and importance in various 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
    immers
    -0.06
     rap
    -0.06
    è£ķ
    -0.06
    467
    -0.06
    »
    -0.06
     Nem
    -0.06
    Ñĸдом
    -0.06
    vise
    -0.06
     Will
    -0.06
     refresh
    -0.06
    POSITIVE LOGITS
     importance
    0.11
     Importance
    0.09
    опол
    0.08
    ffi
    0.08
     importante
    0.07
    _IMPORT
    0.07
    /import
    0.07
    -important
    0.07
     Ïĥη
    0.07
    éĩįè¦ģ
    0.07
    Activations Density 0.032%

    No Known Activations