© 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. 28915
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their management

    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
    _ioctl
    -0.06
    STE
    -0.06
    defaults
    -0.06
    Ìģc
    -0.06
     apro
    -0.06
    èĦij
    -0.06
     tartÄ±ÅŁ
    -0.06
    _locale
    -0.06
    blade
    -0.06
    okud
    -0.06
    POSITIVE LOGITS
     symptoms
    0.09
    rega
    0.08
     symptom
    0.07
     Symptoms
    0.07
     symp
    0.07
    sym
    0.07
    rschein
    0.07
    .sym
    0.06
    orny
    0.06
    enti
    0.06
    Activations Density 0.015%

    No Known Activations