© 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. 89561
    Prev
    Next
    INDEX
    Explanations

    anatomical features and physical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    stroy
    -0.08
    .sul
    -0.08
    ingers
    -0.08
    eus
    -0.08
    над
    -0.07
    uyu
    -0.07
    Interop
    -0.07
     caval
    -0.07
    uhl
    -0.07
    ezi
    -0.07
    POSITIVE LOGITS
     syndrome
    0.06
     compared
    0.06
    lessness
    0.06
    -less
    0.06
     Ly
    0.05
     with
    0.05
     IIC
    0.05
     inherited
    0.05
    nP
    0.05
     Syndrome
    0.05
    Activations Density 0.033%

    No Known Activations