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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83464
    Prev
    Next
    INDEX
    Explanations

    terms related to physical operations and symptoms associated with health conditions

    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
    ?}",
    -0.07
    @student
    -0.07
    jom
    -0.07
    पत
    -0.07
    adden
    -0.07
    avn
    -0.07
    å°¾
    -0.07
    ulpt
    -0.07
    $_['
    -0.06
    lesai
    -0.06
    POSITIVE LOGITS
     Epid
    0.07
    GD
    0.07
     arms
    0.07
    gd
    0.06
     Arms
    0.06
     involvement
    0.06
     Duration
    0.06
     Nico
    0.06
     limbs
    0.06
     defending
    0.06
    Activations Density 0.002%

    No Known Activations