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

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 96714
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and titles

    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
    kou
    -0.07
    eras
    -0.07
    abez
    -0.07
    วย
    -0.07
    kov
    -0.07
     Todd
    -0.06
    ɵ
    -0.06
    quez
    -0.06
    åłĤ
    -0.06
    oya
    -0.06
    POSITIVE LOGITS
    orman
    0.08
    åĩĮ
    0.07
     Polish
    0.07
    (delegate
    0.07
    hsi
    0.07
    inton
    0.07
     boom
    0.06
     Bros
    0.06
     Poland
    0.06
    ulin
    0.06
    Activations Density 0.224%

    No Known Activations