© 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. 70912
    Prev
    Next
    INDEX
    Explanations

    references to libraries or components in code

    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
    è¼
    -0.08
    usra
    -0.07
     cara
    -0.07
     Kinh
    -0.07
    ÑĢÑĥ
    -0.07
     vrou
    -0.07
     exactly
    -0.06
    eday
    -0.06
    rese
    -0.06
    ged
    -0.06
    POSITIVE LOGITS
     TaÅŁ
    0.07
    _INC
    0.06
    ature
    0.06
     Aydın
    0.06
     Lambert
    0.06
     rap
    0.06
    ARGV
    0.06
    ili
    0.06
     Piet
    0.06
     Umb
    0.06
    Activations Density 0.000%

    No Known Activations