© 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. 116974
    Prev
    Next
    INDEX
    Explanations

    references to smartphones

    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
    ibles
    -0.08
    axed
    -0.07
    ration
    -0.07
    otype
    -0.07
    iber
    -0.07
    rious
    -0.07
    atom
    -0.06
    ibold
    -0.06
    ustin
    -0.06
    avir
    -0.06
    POSITIVE LOGITS
    /table
    0.11
    /Table
    0.09
    elik
    0.08
    端
    0.07
    /i
    0.07
    son
    0.07
    /com
    0.06
    ../../../
    0.06
    oque
    0.06
    -readable
    0.06
    Activations Density 0.004%

    No Known Activations