© 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. 79594
    Prev
    Next
    INDEX
    Explanations

    negative imperatives and expressions of caution

    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
    aul
    -0.06
    .twig
    -0.06
    Coordinates
    -0.06
     IW
    -0.06
    gra
    -0.06
    Coordinate
    -0.06
    rael
    -0.06
    ...">↵
    -0.06
    heel
    -0.06
    690
    -0.06
    POSITIVE LOGITS
     altogether
    0.09
    ä¿Ĭ
    0.08
     bother
    0.08
    inka
    0.07
    ãĥĥãĤ«ãĥ¼
    0.07
    selectors
    0.07
    CKER
    0.06
    pressor
    0.06
    tempt
    0.06
    chooser
    0.06
    Activations Density 0.030%

    No Known Activations