© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71437
    Prev
    Next
    INDEX
    Explanations

    instances of player names and terms associated with sports legitimacy

    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
    rán
    -0.07
    _CN
    -0.07
    .IntPtr
    -0.07
     Hart
    -0.07
    عد
    -0.07
    ãĥĸãĥª
    -0.07
    serter
    -0.07
    å´İ
    -0.07
    Uvs
    -0.07
     Barton
    -0.06
    POSITIVE LOGITS
     Violence
    0.06
     violence
    0.06
     Domestic
    0.06
     Baltimore
    0.06
    bie
    0.06
    enu
    0.06
    201
    0.06
     domestic
    0.06
    elfare
    0.06
    lood
    0.06
    Activations Density 0.000%

    No Known Activations