© 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. 53747
    Prev
    Next
    INDEX
    Explanations

    elements related to images and graphical content in the document

    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
    odox
    -0.08
    æĮ¯
    -0.07
    itesse
    -0.07
     Slee
    -0.07
    iele
    -0.07
    lew
    -0.07
    RITE
    -0.07
    γÏī
    -0.06
    sterol
    -0.06
    emies
    -0.06
    POSITIVE LOGITS
     falling
    0.06
     fall
    0.06
     Amp
    0.06
    dek
    0.06
    riel
    0.06
    endif
    0.06
     seal
    0.06
    arp
    0.06
     Patri
    0.06
    icone
    0.06
    Activations Density 0.028%

    No Known Activations