© 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. 92913
    Prev
    Next
    INDEX
    Explanations

    verbs related to granting permission or capability

    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
    ula
    -0.07
    /or
    -0.07
    IRR
    -0.07
    ulerAngles
    -0.07
    drs
    -0.07
    orida
    -0.07
    obar
    -0.06
    ằng
    -0.06
    ditor
    -0.06
    ysi
    -0.06
    POSITIVE LOGITS
     us
    0.12
     them
    0.09
     you
    0.07
    ces
    0.07
     we
    0.07
    529
    0.06
     him
    0.06
    swer
    0.06
     organ
    0.06
    840
    0.06
    Activations Density 0.027%

    No Known Activations