© 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. 31239
    Prev
    Next
    INDEX
    Explanations

    conditions or situations that imply danger or risk of extinction

    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
    ingo
    -0.07
    ãĤ¤ãĥ¤
    -0.07
    ddit
    -0.07
    екÑģи
    -0.07
    æĨ
    -0.07
     Tune
    -0.07
    infos
    -0.07
     misc
    -0.06
    ι
    -0.06
    /misc
    -0.06
    POSITIVE LOGITS
     Gone
    0.07
     gone
    0.07
     portions
    0.07
    aker
    0.07
     entire
    0.06
    elli
    0.06
     parts
    0.06
    enger
    0.06
    vae
    0.06
     Entire
    0.06
    Activations Density 0.043%

    No Known Activations