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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84530
    Prev
    Next
    INDEX
    Explanations

    references to medical situations and hospital settings during conflict

    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
    oure
    -0.09
    utut
    -0.07
    arendra
    -0.07
    sdale
    -0.07
    grese
    -0.07
    stå
    -0.07
    .Annotations
    -0.07
    escort
    -0.07
    ihad
    -0.06
    à¸±à¸Ľ
    -0.06
    POSITIVE LOGITS
     improvis
    0.08
     improv
    0.06
     admissions
    0.06
     bay
    0.06
     mort
    0.06
    ãĥ¼ãĥ©
    0.06
     Bans
    0.06
    alan
    0.06
     improvised
    0.06
    allo
    0.06
    Activations Density 0.021%

    No Known Activations