© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62155
    Prev
    Next
    INDEX
    Explanations

    references to side effects and health impacts related to treatments or medications

    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
    ovit
    -0.08
    atta
    -0.07
    .prototype
    -0.07
    amas
    -0.07
    ampo
    -0.06
    ssel
    -0.06
    кÑĥлÑı
    -0.06
    ampil
    -0.06
    _macro
    -0.06
     ÙĤرار
    -0.06
    POSITIVE LOGITS
     side
    0.17
     Side
    0.15
    åī¯
    0.14
     SIDE
    0.14
    Side
    0.13
    side
    0.13
    _side
    0.11
    (side
    0.11
    SIDE
    0.10
    	side
    0.10
    Activations Density 0.086%

    No Known Activations