© 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. 2558
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking care of various responsibilities or entities

    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
    /OR
    -0.07
    ka
    -0.07
    /or
    -0.07
    hiro
    -0.06
    re
    -0.06
    yles
    -0.06
     onto
    -0.06
     Scha
    -0.06
    anth
    -0.06
    loha
    -0.06
    POSITIVE LOGITS
    /mit
    0.08
    ooter
    0.08
    afen
    0.07
    lsen
    0.07
     ìĤ¬íķŃ
    0.07
    inaire
    0.06
     thÃŃ
    0.06
    gradable
    0.06
    375
    0.06
     exempt
    0.06
    Activations Density 0.007%

    No Known Activations