© 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. 42826
    Prev
    Next
    INDEX
    Explanations

    numerical or comparative data points related to medical or technological contexts

    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
    B
    -0.06
    A
    -0.06
    bridge
    -0.06
    erez
    -0.05
    annon
    -0.05
    amo
    -0.05
    U
    -0.05
    =explode
    -0.05
    esign
    -0.05
    apiro
    -0.05
    POSITIVE LOGITS
     other
    0.31
     others
    0.27
    other
    0.24
    åħ¶ä»ĸ
    0.24
     anderen
    0.23
    others
    0.23
     autres
    0.23
     otros
    0.22
     åħ¶ä»ĸ
    0.21
     andere
    0.21
    Activations Density 0.080%

    No Known Activations