© 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. 9-LLAMASCOPE-RES-131K
    11. 99015
    Prev
    Next
    INDEX
    Explanations

    specific personal names and their connections in a narrative context

    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
    achable
    -0.08
    jerne
    -0.08
    åde
    -0.07
     Nack
    -0.07
    ESCO
    -0.07
    داÙĨÙĦÙĪد
    -0.07
    uslim
    -0.07
    izik
    -0.07
    161
    -0.07
    Porno
    -0.07
    POSITIVE LOGITS
    cn
    0.07
    amm
    0.06
    Ìģ
    0.06
    lund
    0.06
    821
    0.05
    anno
    0.05
     gifted
    0.05
    xdc
    0.05
    Anywhere
    0.05
    yp
    0.05
    Activations Density 0.040%

    No Known Activations