© 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. 22-LLAMASCOPE-RES-131K
    11. 4321
    Prev
    Next
    INDEX
    Explanations

    consistent patterns of kindness and giving in relationships

    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
    ashboard
    -0.07
    amos
    -0.07
    igor
    -0.07
    789
    -0.07
    lemen
    -0.06
    idges
    -0.06
     báºŃc
    -0.06
    好ãģį
    -0.06
    uae
    -0.06
    ünchen
    -0.06
    POSITIVE LOGITS
    -available
    0.09
     available
    0.09
     ready
    0.08
    ready
    0.08
     smile
    0.08
     disponible
    0.07
     willing
    0.07
    _available
    0.07
    Available
    0.07
     Available
    0.07
    Activations Density 0.013%

    No Known Activations