© 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 EvalsExportsinterp-engineNEWAPI 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. 77807
    Prev
    Next
    INDEX
    Explanations

    references to formal communications or letters related to regulatory or legal matters

    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
     announcements
    -0.06
    elen
    -0.06
    uits
    -0.06
    ordon
    -0.06
     Guard
    -0.06
    ammer
    -0.06
    abs
    -0.05
     grand
    -0.05
     grab
    -0.05
    jom
    -0.05
    POSITIVE LOGITS
     letter
    0.14
    letter
    0.12
     Letter
    0.12
     LETTER
    0.11
    -letter
    0.11
    Letter
    0.11
    _letter
    0.10
    (letter
    0.10
     addressed
    0.09
     letters
    0.09
    Activations Density 0.034%

    No Known Activations