© 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. 55155
    Prev
    Next
    INDEX
    Explanations

    references to safety in outdoor and public settings

    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
    inx
    -0.07
    ÙĪÙĤÙģ
    -0.07
    phin
    -0.07
    ahan
    -0.07
    urst
    -0.06
    lod
    -0.06
    ayar
    -0.06
    ضاÙĨ
    -0.06
     kaz
    -0.06
    llib
    -0.06
    POSITIVE LOGITS
     travelling
    0.08
     traveling
    0.07
     travels
    0.07
     NavParams
    0.07
    Ïīν
    0.06
    758
    0.06
     playing
    0.06
     outdoors
    0.06
     travel
    0.06
    .ci
    0.06
    Activations Density 0.019%

    No Known Activations