© 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. 15-LLAMASCOPE-RES-131K
    11. 86033
    Prev
    Next
    INDEX
    Explanations

    critical assessments of programs or initiatives

    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
    ugu
    -0.07
    ayi
    -0.06
    igu
    -0.06
    539
    -0.06
    555
    -0.06
     completeness
    -0.06
    IGHL
    -0.06
    æ£
    -0.06
    EEE
    -0.06
     typ
    -0.05
    POSITIVE LOGITS
     justify
    0.10
     justification
    0.10
    justify
    0.09
     justified
    0.08
    ussen
    0.07
    uments
    0.07
    anness
    0.06
    bons
    0.06
    æĻ¶
    0.06
    ients
    0.06
    Activations Density 0.046%

    No Known Activations