© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83956
    Prev
    Next
    INDEX
    Explanations

    complex non-English characters or symbols

    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
    Ìĥ
    -0.07
    azines
    -0.07
    899
    -0.07
    ÌĨ
    -0.07
    sey
    -0.07
    less
    -0.07
    è·µ
    -0.07
    sto
    -0.07
    åı¥è¯Ŀ
    -0.07
     гÑĢÑĥд
    -0.07
    POSITIVE LOGITS
    inker
    0.07
    ialog
    0.06
    nelle
    0.06
    IZER
    0.06
    æĢ§
    0.06
    /logger
    0.06
     Unidos
    0.06
    åύ
    0.06
    uez
    0.06
    ÑĢаÑĤно
    0.06
    Activations Density 0.005%

    No Known Activations