© 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. 2733
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical and 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
    å±¥
    -0.07
     predominant
    -0.07
    vard
    -0.06
    eq
    -0.06
    >:</
    -0.06
     jich
    -0.06
     Pred
    -0.06
    utch
    -0.06
     pred
    -0.06
    ymb
    -0.06
    POSITIVE LOGITS
    illos
    0.07
     causes
    0.07
    rnd
    0.07
    ãĥ¼ãĤ¸
    0.07
     Joi
    0.07
     valign
    0.06
     stan
    0.06
    ána
    0.06
    enschaft
    0.06
    ĽĦ
    0.06
    Activations Density 0.034%

    No Known Activations