© 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. 31587
    Prev
    Next
    INDEX
    Explanations

    XML namespace declarations

    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
    ammo
    -0.07
    alace
    -0.06
    edes
    -0.06
    Pear
    -0.06
     Pearl
    -0.06
    irm
    -0.06
     Poh
    -0.06
    cott
    -0.06
     pearls
    -0.06
    _atts
    -0.06
    POSITIVE LOGITS
    arin
    0.07
    UsageId
    0.07
    è·¡
    0.07
    TestCategory
    0.07
    985
    0.06
    迹
    0.06
    itas
    0.06
    ýt
    0.06
    ÙĶ
    0.06
    OffsetTable
    0.06
    Activations Density 0.000%

    No Known Activations