© 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. 27083
    Prev
    Next
    INDEX
    Explanations

    terms related to language translation and interpretation

    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
    å½Ĵ
    -0.07
    enia
    -0.06
    inis
    -0.06
     sexually
    -0.06
    isz
    -0.06
    peri
    -0.06
     aw
    -0.06
     gy
    -0.06
     Greenwich
    -0.06
     gir
    -0.05
    POSITIVE LOGITS
     flu
    0.07
    speaker
    0.07
    -spe
    0.07
     profession
    0.07
     Flu
    0.07
     AudioManager
    0.07
     Prel
    0.07
    _echo
    0.07
     professionalism
    0.07
    _mt
    0.07
    Activations Density 0.005%

    No Known Activations