© 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. 95908
    Prev
    Next
    INDEX
    Explanations

    terms associated with various issues and challenges related to health and dietary restrictions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    asca
    -0.08
    ocha
    -0.07
    Ìģc
    -0.07
    ené
    -0.07
    _OW
    -0.07
    panÄĽl
    -0.07
    inke
    -0.07
    dirty
    -0.07
    ÑĢÑĥж
    -0.07
    allee
    -0.07
    POSITIVE LOGITS
    less
    0.15
    -free
    0.14
    -less
    0.13
    -Free
    0.12
     no
    0.11
    LESS
    0.11
     free
    0.10
     zero
    0.10
    lessness
    0.10
     neither
    0.10
    Activations Density 0.018%

    No Known Activations