© 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. 125320
    Prev
    Next
    INDEX
    Explanations

    dialogue or quotes from individuals 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
     Dahl
    -0.07
    uhan
    -0.06
    habi
    -0.06
    SSF
    -0.06
    ubat
    -0.06
    коÑĤ
    -0.06
    ÃŃcul
    -0.06
    ุà¸Ĺ
    -0.06
    mailto
    -0.06
    ayout
    -0.06
    POSITIVE LOGITS
    AZY
    0.07
    uis
    0.07
     çº
    0.06
    EUR
    0.06
    lig
    0.06
    entiful
    0.06
    eah
    0.06
    ÅĻet
    0.06
    686
    0.06
    赤
    0.06
    Activations Density 0.010%

    No Known Activations