© 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. 93568
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements

    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
    illet
    -0.07
    chia
    -0.06
    alis
    -0.06
    enne
    -0.06
     pix
    -0.06
    ichen
    -0.06
    ajan
    -0.06
    aturity
    -0.06
    ï¼Īå¹³æĪIJ
    -0.06
    arie
    -0.06
    POSITIVE LOGITS
    idor
    0.07
    ¯u
    0.06
     Guar
    0.06
    _FAULT
    0.06
     rencont
    0.06
    ela
    0.06
    -fontawesome
    0.06
    رÙĪز
    0.06
    éĻ¸
    0.06
     rele
    0.06
    Activations Density 0.001%

    No Known Activations