© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127871
    Prev
    Next
    INDEX
    Explanations

    references to legal or political accountability

    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
     INCIDENT
    -0.07
    заб
    -0.07
    æĸ
    -0.06
    esser
    -0.06
    (typ
    -0.06
    -Identifier
    -0.06
    ãĥªãĤ¢
    -0.06
     Redistribution
    -0.06
    uluk
    -0.06
    eb
    -0.06
    POSITIVE LOGITS
    uzzi
    0.08
    Ñıн
    0.07
    azio
    0.07
     investigation
    0.07
     investigations
    0.07
     Russia
    0.07
     witch
    0.07
    gate
    0.06
     impe
    0.06
    witch
    0.06
    Activations Density 0.072%

    No Known Activations