© 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. 108134
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequencies

    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
    cho
    -0.06
    enschaft
    -0.06
     ins
    -0.06
     Schultz
    -0.06
    avic
    -0.06
    _MUL
    -0.06
    337
    -0.06
    ummies
    -0.06
    uat
    -0.06
    .mutable
    -0.06
    POSITIVE LOGITS
    aira
    0.08
    #
    0.07
    ÐIJÑĢÑħÑĸв
    0.07
    acity
    0.06
    OUNDS
    0.06
    stants
    0.06
    .ascii
    0.06
    _DECL
    0.06
    YRO
    0.06
    NCY
    0.06
    Activations Density 0.035%

    No Known Activations