Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95649
    Prev
    Next
    INDEX
    Explanations

    statements about capability and support

    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
    annels
    -0.06
    edback
    -0.06
    eres
    -0.06
    kova
    -0.06
     oneself
    -0.06
    friends
    -0.06
     appe
    -0.06
    ero
    -0.06
    lint
    -0.06
    gee
    -0.05
    POSITIVE LOGITS
    dek
    0.07
    idir
    0.07
     Chop
    0.07
     ("-
    0.07
    ãĥ¼ãĥĹ
    0.06
    inea
    0.06
    üyük
    0.06
     Solo
    0.06
     correspondent
    0.06
    teste
    0.06
    Activations Density 0.015%

    No Known Activations