© 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. 27887
    Prev
    Next
    INDEX
    Explanations

    data structures or arrays

    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
    нен
    -0.07
    $MESS
    -0.07
     ucwords
    -0.06
     (*((
    -0.06
    ArrayOf
    -0.06
    isÃŃ
    -0.06
    ữ
    -0.06
    $LANG
    -0.06
     Surround
    -0.06
    658
    -0.06
    POSITIVE LOGITS
    arhus
    0.06
    uda
    0.06
    uba
    0.06
    omb
    0.06
    nis
    0.06
    ento
    0.06
    anta
    0.06
    ule
    0.06
     Bund
    0.06
    reet
    0.05
    Activations Density 0.003%

    No Known Activations