© 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. 30385
    Prev
    Next
    INDEX
    Explanations

    phrases that convey instructional guidance or the presentation of information

    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
    ¶Į
    -0.07
    iyah
    -0.07
    enties
    -0.07
     Hava
    -0.07
    icens
    -0.06
    дÑĢом
    -0.06
     oneself
    -0.06
    ender
    -0.06
    αι
    -0.06
    erg
    -0.06
    POSITIVE LOGITS
    .fm
    0.07
    itals
    0.06
    jak
    0.06
     nob
    0.06
     GU
    0.06
    irit
    0.06
    ichert
    0.06
    ãĤıãģļ
    0.06
    yre
    0.06
    nob
    0.05
    Activations Density 0.017%

    No Known Activations