© 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. 125903
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, particularly those related to a specific event or recognition

    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
    Mot
    -0.07
    ensch
    -0.06
    ilst
    -0.06
    alles
    -0.06
    hev
    -0.06
     ethnic
    -0.06
    avigation
    -0.06
     Anaheim
    -0.06
    gx
    -0.06
    ifting
    -0.06
    POSITIVE LOGITS
    æ¡IJ
    0.08
     Cla
    0.08
     Yale
    0.07
     Executors
    0.07
    åīij
    0.07
     polo
    0.07
    ilim
    0.07
     Gund
    0.06
    ogo
    0.06
    .setDefault
    0.06
    Activations Density 0.099%

    No Known Activations