© 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. 118703
    Prev
    Next
    INDEX
    Explanations

    references to numerical or ordinal indicators

    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
    rava
    -0.09
    iÄį
    -0.08
    меÑĩ
    -0.07
    itudes
    -0.07
    égor
    -0.07
    SKI
    -0.07
    uš
    -0.07
    assel
    -0.07
    imer
    -0.07
     extrem
    -0.07
    POSITIVE LOGITS
     of
    0.10
    aleigh
    0.07
     của
    0.07
    bay
    0.06
    :
    0.06
    crest
    0.06
    FG
    0.05
    bine
    0.05
    ãģ¤
    0.05
    ibel
    0.05
    Activations Density 0.052%

    No Known Activations