© 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. 57404
    Prev
    Next
    INDEX
    Explanations

    occurrences of letters or word patterns, particularly related to spelling and the alphabet

    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
     Beans
    -0.06
    gos
    -0.06
    raq
    -0.06
    лоÑĩ
    -0.06
    mq
    -0.06
    oe
    -0.06
    atus
    -0.05
    acker
    -0.05
     Lone
    -0.05
     extraction
    -0.05
    POSITIVE LOGITS
     letter
    0.14
    letter
    0.13
    _letter
    0.12
     Letter
    0.12
     letters
    0.12
    letters
    0.12
    Letter
    0.11
    -letter
    0.11
     LETTER
    0.11
    (letter
    0.10
    Activations Density 0.023%

    No Known Activations