© 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. 116338
    Prev
    Next
    INDEX
    Explanations

    expressions indicating availability or ease of access

    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
    llib
    -0.07
    achs
    -0.07
    ETHOD
    -0.07
    csi
    -0.07
    gia
    -0.07
    imson
    -0.07
     fatt
    -0.06
    alles
    -0.06
    ième
    -0.06
    odash
    -0.06
    POSITIVE LOGITS
     dÃłng
    0.09
    illy
    0.07
    ings
    0.07
     بÙĪابة
    0.07
    rosse
    0.06
    ily
    0.06
    ort
    0.06
    ign
    0.06
    YZ
    0.06
    iest
    0.06
    Activations Density 0.004%

    No Known Activations