© 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. 72160
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to object-oriented principles and method definitions

    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
    öst
    -0.07
    laps
    -0.07
    ÏĩÏĮ
    -0.07
    .mit
    -0.07
    mitter
    -0.06
    itel
    -0.06
    &C
    -0.06
    Clo
    -0.06
    à¥ģमत
    -0.06
    oretical
    -0.06
    POSITIVE LOGITS
    roz
    0.07
    acre
    0.07
     Schwarz
    0.06
    iesel
    0.06
    pcodes
    0.06
     grav
    0.06
    tach
    0.06
    esity
    0.06
    rello
    0.06
    481
    0.06
    Activations Density 0.001%

    No Known Activations