© 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. 77075
    Prev
    Next
    INDEX
    Explanations

    references to fictional or mythical characters and their descriptions

    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
     Pearce
    -0.07
     Cousins
    -0.07
    æĺĩ
    -0.07
    kud
    -0.07
    æĻ´
    -0.07
    å®ĥ们
    -0.07
    azÄĥ
    -0.06
     vej
    -0.06
    myp
    -0.06
    yg
    -0.06
    POSITIVE LOGITS
     name
    0.11
     whom
    0.09
     mentioned
    0.08
    åIJįåŃĹ
    0.08
     mention
    0.08
    .name
    0.08
     tên
    0.07
    -name
    0.07
    name
    0.07
     nowhere
    0.07
    Activations Density 0.021%

    No Known Activations