© 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. 116829
    Prev
    Next
    INDEX
    Explanations

    sequences of characters and formatting in code or programming syntax

    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
    dney
    -0.08
    htdocs
    -0.08
    åĵģ
    -0.08
    ecided
    -0.07
    ledon
    -0.07
    edores
    -0.07
    odega
    -0.07
    committed
    -0.07
    endtime
    -0.07
    ewood
    -0.07
    POSITIVE LOGITS
    uba
    0.07
    ije
    0.07
     Subtract
    0.07
     shift
    0.06
     SHIFT
    0.06
    _letter
    0.06
     letter
    0.06
     Letter
    0.06
    SHIFT
    0.06
     letters
    0.06
    Activations Density 0.014%

    No Known Activations