© 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. 9-LLAMASCOPE-RES-131K
    11. 98869
    Prev
    Next
    INDEX
    Explanations

    words indicating access control levels in programming contexts

    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
    icontrol
    -0.07
    irut
    -0.07
    ghest
    -0.07
    ukkan
    -0.07
    orca
    -0.07
    arend
    -0.07
    idget
    -0.06
    osi
    -0.06
    irma
    -0.06
    ä¿
    -0.06
    POSITIVE LOGITS
    uzzi
    0.08
    997
    0.07
    234
    0.06
    148
    0.06
    297
    0.06
     Ng
    0.06
     fixed
    0.06
     hol
    0.06
    570
    0.06
    572
    0.06
    Activations Density 0.002%

    No Known Activations