© 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. 15-LLAMASCOPE-RES-131K
    11. 89093
    Prev
    Next
    INDEX
    Explanations

    mentions of academic transcripts and medical records related to applications

    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
    endl
    -0.07
    endo
    -0.06
    ufe
    -0.06
    ãĤ¢ãĥ³
    -0.06
    vert
    -0.06
    kas
    -0.06
    976
    -0.06
     Magazine
    -0.06
     depart
    -0.06
    ti
    -0.06
    POSITIVE LOGITS
    upplier
    0.08
    uin
    0.07
    ourke
    0.07
    .Tool
    0.07
    uced
    0.07
    upply
    0.07
    egade
    0.07
    azu
    0.06
    untime
    0.06
    ospace
    0.06
    Activations Density 0.001%

    No Known Activations