© 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. 17-LLAMASCOPE-RES-131K
    11. 88480
    Prev
    Next
    INDEX
    Explanations

    formal affirmations and conclusions in legal or official contexts

    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
    iasi
    -0.08
    ýš
    -0.07
     Método
    -0.07
     testify
    -0.06
     Metodo
    -0.06
    uers
    -0.06
     migrationBuilder
    -0.06
     buurt
    -0.06
    udeau
    -0.06
    urvey
    -0.06
    POSITIVE LOGITS
    anus
    0.06
    ega
    0.06
    erie
    0.06
    peri
    0.06
     neither
    0.06
    /find
    0.06
    eteria
    0.06
     abs
    0.06
     finds
    0.06
    ÑĤÑĢон
    0.06
    Activations Density 0.020%

    No Known Activations