© 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. 17-LLAMASCOPE-RES-131K
    11. 26868
    Prev
    Next
    INDEX
    Explanations

    references to arrests and legal proceedings

    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
     switch
    -0.06
    illard
    -0.06
    stad
    -0.06
    acho
    -0.06
    switch
    -0.06
    andin
    -0.06
    andi
    -0.05
     switches
    -0.05
    EdgeInsets
    -0.05
    æī§
    -0.05
    POSITIVE LOGITS
     Weston
    0.07
    isen
    0.07
     Sexe
    0.07
    ibel
    0.07
    arget
    0.07
     Polar
    0.07
    frauen
    0.07
    arged
    0.07
    oled
    0.07
    apor
    0.07
    Activations Density 0.003%

    No Known Activations