© 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. 93578
    Prev
    Next
    INDEX
    Explanations

    non-English characters or symbols, particularly those related to various languages or scripts

    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
    zt
    -0.07
    اا
    -0.07
    úng
    -0.07
    roid
    -0.06
    iker
    -0.06
    roids
    -0.06
    udence
    -0.06
    iale
    -0.06
    ëĶĶìĭľ
    -0.06
    ocs
    -0.06
    POSITIVE LOGITS
    ľ
    0.09
    Ľ
    0.08
    ¬
    0.08
    ¯
    0.07
    ¡
    0.07
    IJ
    0.07
    ļ
    0.07
    ¸
    0.07
    ķ
    0.06
    Ļ
    0.06
    Activations Density 0.001%

    No Known Activations