© 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. 53971
    Prev
    Next
    INDEX
    Explanations

    academic degrees and qualifications

    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
    Å¡it
    -0.08
    artz
    -0.08
    @student
    -0.08
    à¸Ķย
    -0.07
    iscard
    -0.07
    ulumi
    -0.07
    vell
    -0.07
    ifer
    -0.07
    andest
    -0.07
    uchen
    -0.07
    POSITIVE LOGITS
    ent
    0.06
     fore
    0.06
    c
    0.05
    n
    0.05
    1
    0.05
    uml
    0.05
     nodes
    0.05
    x
    0.05
     fine
    0.05
     bekom
    0.05
    Activations Density 0.007%

    No Known Activations