Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43732
    Prev
    Next
    INDEX
    Explanations

    terms related to emotional or physiological responses

    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
    ยà¸ĩ
    -0.07
     Opport
    -0.07
    онаÑħ
    -0.07
    ichi
    -0.07
    Ä±ÅŁÄ±k
    -0.06
    иÑĩна
    -0.06
    _SHADOW
    -0.06
    uteur
    -0.06
    lox
    -0.06
    okino
    -0.06
    POSITIVE LOGITS
     facial
    0.14
     emotion
    0.14
     emotional
    0.13
     emotions
    0.12
     Facial
    0.12
     Emotional
    0.11
     anger
    0.11
     affect
    0.11
     val
    0.11
     Ek
    0.11
    Activations Density 0.015%

    No Known Activations