© 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. 104543
    Prev
    Next
    INDEX
    Explanations

    instances of data manipulation or coding functions

    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
    astos
    -0.07
    izzo
    -0.07
    _timing
    -0.07
    strup
    -0.07
     Fle
    -0.07
    _Generic
    -0.07
    beck
    -0.07
    _ENDIAN
    -0.06
    ë©
    -0.06
    HQ
    -0.06
    POSITIVE LOGITS
    bsd
    0.07
    arih
    0.06
    igli
    0.06
     cad
    0.06
    itom
    0.06
     whereabouts
    0.06
    enny
    0.06
     lev
    0.05
    igkeit
    0.05
     shallow
    0.05
    Activations Density 0.001%

    No Known Activations