© 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. 93540
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to individual experiences and emotions

    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
    IFO
    -0.07
    ragen
    -0.07
    aleb
    -0.07
     urg
    -0.06
    EATURE
    -0.06
    aec
    -0.06
    agina
    -0.06
    idar
    -0.06
    _DISPATCH
    -0.06
    _commands
    -0.06
    POSITIVE LOGITS
     emotional
    0.10
     Emotional
    0.10
     stress
    0.09
    stress
    0.09
     Stress
    0.09
     emotion
    0.09
     emotions
    0.08
     mood
    0.08
     mental
    0.07
     coping
    0.07
    Activations Density 0.009%

    No Known Activations