© 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. 94951
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly those associated with modules and imports

    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
    books
    -0.07
     Ease
    -0.06
     Downtown
    -0.06
    itzer
    -0.06
    ück
    -0.06
    rou
    -0.06
    avit
    -0.06
    bers
    -0.06
    ini
    -0.06
    508
    -0.06
    POSITIVE LOGITS
    ñana
    0.08
    frauen
    0.07
    _SDK
    0.07
    .setDefault
    0.07
    èĩ
    0.07
    ½Ķ
    0.07
    krom
    0.07
     explan
    0.06
    AGMA
    0.06
    liš
    0.06
    Activations Density 0.011%

    No Known Activations