© 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. 27939
    Prev
    Next
    INDEX
    Explanations

    instances of the word "crash" and related terms indicating accidents or collisions

    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
    ÑģÑĮ
    -0.08
    ally
    -0.08
    calar
    -0.07
    longleftrightarrow
    -0.07
     bree
    -0.07
    ismatch
    -0.07
    анÑģи
    -0.07
    IZE
    -0.07
     Persistence
    -0.07
    984
    -0.06
    POSITIVE LOGITS
    (es
    0.11
    bum
    0.08
    es
    0.08
    y
    0.08
    ãĥ«ãĥī
    0.08
    ses
    0.08
    mer
    0.08
    leigh
    0.08
    گاÙĩ
    0.07
    eroon
    0.07
    Activations Density 0.008%

    No Known Activations