© 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. 42818
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and research articles

    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
    érica
    -0.07
     Rosenstein
    -0.07
    .inject
    -0.06
    eck
    -0.06
    ough
    -0.05
    avax
    -0.05
     redirection
    -0.05
    jun
    -0.05
    123
    -0.05
    èĶµ
    -0.05
    POSITIVE LOGITS
    ÅĻen
    0.07
    idelberg
    0.07
    DOI
    0.07
    ulu
    0.07
    orado
    0.07
    steller
    0.07
    outu
    0.07
     suggest
    0.07
    ãĥ¤
    0.06
    ÑĤÑİ
    0.06
    Activations Density 0.013%

    No Known Activations