© 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. 86203
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that suggest recommendations or advice

    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
    ont
    -0.06
    inde
    -0.06
    zin
    -0.06
    gel
    -0.06
    gba
    -0.06
    ju
    -0.06
    asm
    -0.05
     redundancy
    -0.05
     Lans
    -0.05
    ulan
    -0.05
    POSITIVE LOGITS
     Gam
    0.07
    /***/
    0.07
    ldr
    0.07
    ednou
    0.07
    Gam
    0.07
    MEA
    0.07
     Neutral
    0.06
    FRING
    0.06
    akis
    0.06
    .want
    0.06
    Activations Density 0.015%

    No Known Activations