© 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. 1172
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial expectations and outcomes

    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
    erb
    -0.07
    è¦
    -0.07
    oco
    -0.07
    foy
    -0.07
    ollo
    -0.07
    elin
    -0.07
    vim
    -0.06
    OMET
    -0.06
    quisitions
    -0.06
    owell
    -0.06
    POSITIVE LOGITS
     Blasio
    0.07
     èŃ
    0.06
    .zip
    0.06
    teki
    0.06
    aghetti
    0.06
     nowhere
    0.06
    iance
    0.06
    é½IJ
    0.06
     à¤Ĩय
    0.06
     Success
    0.06
    Activations Density 0.001%

    No Known Activations