© 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. 28888
    Prev
    Next
    INDEX
    Explanations

    words related to emotional and physical states, particularly concerning health and well-being

    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
    obo
    -0.07
    ald
    -0.07
     ÐŁÐ¾Ð¼
    -0.07
    wide
    -0.07
    -wide
    -0.06
    agen
    -0.06
    ÙĬات
    -0.06
     pom
    -0.06
    ALA
    -0.06
    ands
    -0.06
    POSITIVE LOGITS
    ness
    0.13
    NESS
    0.12
    ityEngine
    0.08
     بÙĪدÙĨ
    0.07
    .man
    0.07
    _firestore
    0.07
    nes
    0.07
    ailable
    0.07
     ness
    0.06
    /WebAPI
    0.06
    Activations Density 0.050%

    No Known Activations