© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28931
    Prev
    Next
    INDEX
    Explanations

    references to mental and physical 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
    upe
    -0.07
    éŃĤ
    -0.07
    onta
    -0.07
    Pocket
    -0.07
    اÙĨÚ¯
    -0.06
     bụ
    -0.06
    kir
    -0.06
    .act
    -0.06
    dz
    -0.06
    \core
    -0.06
    POSITIVE LOGITS
    Sym
    0.06
     symptom
    0.06
    imenti
    0.06
    sym
    0.06
    fter
    0.06
     unknown
    0.06
     Symptoms
    0.06
     symptoms
    0.06
     sym
    0.06
     due
    0.06
    Activations Density 0.026%

    No Known Activations