© 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. 125846
    Prev
    Next
    INDEX
    Explanations

    expressions related to motivation and emotional states

    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
     uns
    -0.07
     Uns
    -0.07
     danmark
    -0.06
     Kinder
    -0.06
    ito
    -0.06
    meer
    -0.06
     savage
    -0.06
    kate
    -0.06
    VERS
    -0.06
    kaar
    -0.06
    POSITIVE LOGITS
    nad
    0.08
     Mahm
    0.07
     och
    0.07
     till
    0.07
    ftar
    0.07
    ighet
    0.07
     rash
    0.07
     för
    0.07
    ĩ
    0.07
    för
    0.06
    Activations Density 0.025%

    No Known Activations