© 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. 14324
    Prev
    Next
    INDEX
    Explanations

    sections of technical or coding content

    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
    ajaran
    -0.06
    ihan
    -0.06
    788
    -0.06
     Gould
    -0.06
    ovah
    -0.06
     abs
    -0.06
    993
    -0.06
    ach
    -0.06
    978
    -0.06
    abras
    -0.05
    POSITIVE LOGITS
    Ctrls
    0.08
    нез
    0.07
    .vec
    0.07
    ImagePath
    0.07
     toItem
    0.07
    Äįer
    0.07
    ogg
    0.07
    íĭ
    0.07
    ноÑģÑĤ
    0.07
    nea
    0.07
    Activations Density 0.001%

    No Known Activations