© 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. 4491
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reported" and its variations, indicating references to documented cases or observations

    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
    okit
    -0.07
    hardt
    -0.07
    acre
    -0.06
    ron
    -0.06
    á»ĭch
    -0.06
    kowski
    -0.06
    kf
    -0.06
    æ®ĸ
    -0.06
    ings
    -0.06
    mere
    -0.06
    POSITIVE LOGITS
    iants
    0.07
    775
    0.07
    edly
    0.07
    631
    0.07
    imens
    0.06
    ophon
    0.06
    790
    0.06
    475
    0.06
    836
    0.06
    993
    0.06
    Activations Density 0.008%

    No Known Activations