© 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. 5-LLAMASCOPE-RES-131K
    11. 126599
    Prev
    Next
    INDEX
    Explanations

    quotations or dialogue within the text

    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
    reon
    -0.07
    uire
    -0.07
     Esper
    -0.06
    ë²Į
    -0.06
    å²
    -0.06
    ernals
    -0.06
    üzel
    -0.06
    amik
    -0.06
     Gould
    -0.06
     elabor
    -0.06
    POSITIVE LOGITS
    йн
    0.07
    )prepare
    0.07
    ntag
    0.06
     bi
    0.06
     @}
    0.06
    762
    0.06
    rens
    0.06
    ObjectContext
    0.06
    bi
    0.06
    ẳn
    0.06
    Activations Density 0.027%

    No Known Activations