© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "man."

    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
    orman
    -0.07
    äch
    -0.07
    cers
    -0.06
    vana
    -0.06
    teste
    -0.06
    jure
    -0.06
    âce
    -0.06
    vanished
    -0.06
    gu
    -0.06
    edes
    -0.06
    POSITIVE LOGITS
     multiplic
    0.08
    ascus
    0.07
    /Dk
    0.07
    ků
    0.07
     SPDX
    0.07
    mlink
    0.07
    ĶåĽŀ
    0.07
    enville
    0.06
     sond
    0.06
    нин
    0.06
    Activations Density 0.000%

    No Known Activations