© 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. 14195
    Prev
    Next
    INDEX
    Explanations

    bracketed elements, particularly those related to documentation or programming

    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
    ALCHEMY
    -0.08
    ucz
    -0.08
    aurus
    -0.07
    eda
    -0.07
    ãģ£ãģį
    -0.07
    incinn
    -0.07
    æĽ¸é¤¨
    -0.06
    irth
    -0.06
    ç·Ĵ
    -0.06
    usted
    -0.06
    POSITIVE LOGITS
    landa
    0.07
    aname
    0.06
    apel
    0.06
     slur
    0.06
    alach
    0.06
    chap
    0.06
     todo
    0.06
     mong
    0.06
    æ
    0.06
     view
    0.05
    Activations Density 0.021%

    No Known Activations