© 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. 5828
    Prev
    Next
    INDEX
    Explanations

    titles and names associated with literary works and authors

    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
    unning
    -0.07
     fucks
    -0.07
     Rao
    -0.07
    oler
    -0.06
    iferay
    -0.06
    .Atomic
    -0.06
    schemas
    -0.06
    avl
    -0.06
    -parse
    -0.06
     Fuck
    -0.06
    POSITIVE LOGITS
     cap
    0.07
    DRAM
    0.06
     Higgins
    0.06
     Ober
    0.06
    immers
    0.06
    brook
    0.06
     Ned
    0.06
    bine
    0.06
    pons
    0.06
    CAPE
    0.06
    Activations Density 0.011%

    No Known Activations