© 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. 26992
    Prev
    Next
    INDEX
    Explanations

    references to previous occurrences or experiences

    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
     Excell
    -0.06
     Mum
    -0.06
    вен
    -0.06
    á»±c
    -0.06
    ished
    -0.06
    æ¬
    -0.06
    ằng
    -0.05
     UC
    -0.05
    yd
    -0.05
    dna
    -0.05
    POSITIVE LOGITS
     lui
    0.08
    /current
    0.07
     milion
    0.07
    unei
    0.07
    _COMPILER
    0.07
     INTERRUPTION
    0.07
    preced
    0.07
    HS
    0.06
    нима
    0.06
     ним
    0.06
    Activations Density 0.005%

    No Known Activations