© 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. 81938
    Prev
    Next
    INDEX
    Explanations

    instances of the word "preview" and its variations

    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
    udev
    -0.07
    ala
    -0.07
    keit
    -0.07
    νÏĦ
    -0.07
    WISE
    -0.07
    ãģĿãģĨ
    -0.07
    ода
    -0.06
    enta
    -0.06
    ãĥ³ãĥ
    -0.06
    ago
    -0.06
    POSITIVE LOGITS
    ed
    0.12
    ing
    0.11
    ers
    0.09
    lasting
    0.08
    onder
    0.08
    ingly
    0.07
    ãĥ¥
    0.07
    anian
    0.07
    pane
    0.07
    ably
    0.07
    Activations Density 0.004%

    No Known Activations