© 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. 126892
    Prev
    Next
    INDEX
    Explanations

    specific letters and combinations that likely appear in names or titles

    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
    ouples
    -0.07
    upal
    -0.07
     Squ
    -0.07
    iership
    -0.06
    older
    -0.06
    ÑĮÑİÑĤ
    -0.06
    mares
    -0.06
    ral
    -0.06
    uncia
    -0.06
     couples
    -0.06
    POSITIVE LOGITS
    /el
    0.10
     El
    0.09
    å¿ł
    0.07
    -el
    0.07
    El
    0.06
     dint
    0.06
     ä»»
    0.06
     Echo
    0.06
    æľ
    0.06
    abeth
    0.06
    Activations Density 0.019%

    No Known Activations