© 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. 41766
    Prev
    Next
    INDEX
    Explanations

    phrases related to reassurance and comfort

    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
    eldorf
    -0.08
    emoc
    -0.07
    elda
    -0.07
    ãĥįãĥ«
    -0.07
    代
    -0.07
    ĢìĿ´
    -0.07
    chine
    -0.06
    /from
    -0.06
    anie
    -0.06
    gesch
    -0.06
    POSITIVE LOGITS
     rest
    0.12
     assured
    0.09
     Rest
    0.08
    Rest
    0.08
     rests
    0.07
    (rest
    0.07
    .rest
    0.07
    rest
    0.07
     guarantee
    0.07
     assure
    0.07
    Activations Density 0.002%

    No Known Activations