© 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. 77006
    Prev
    Next
    INDEX
    Explanations

    names and personal identifiers

    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
    Įĵ
    -0.08
    mscorlib
    -0.07
    éal
    -0.07
    .sys
    -0.07
    essler
    -0.07
    Enlarge
    -0.07
    APA
    -0.06
    碼
    -0.06
    endoza
    -0.06
    βά
    -0.06
    POSITIVE LOGITS
     unidentified
    0.07
    strument
    0.06
     unnamed
    0.06
    onen
    0.06
    çĽ
    0.06
    ÅĻÃŃzenÃŃ
    0.06
    iges
    0.06
     multip
    0.06
     born
    0.06
    untas
    0.05
    Activations Density 0.000%

    No Known Activations