© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86004
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate significant challenges or threats

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ime
    -0.08
    sh
    -0.08
    rea
    -0.07
    icity
    -0.07
    vo
    -0.07
    doch
    -0.07
    zan
    -0.07
    tha
    -0.07
    lsen
    -0.07
    shake
    -0.07
    POSITIVE LOGITS
     Ñģобой
    0.08
    idon
    0.08
     threat
    0.07
    este
    0.07
    yonel
    0.07
    ëģĶ
    0.07
    pose
    0.06
    ekk
    0.06
    metics
    0.06
     án
    0.06
    Activations Density 0.007%

    No Known Activations