© 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. 17-LLAMASCOPE-RES-131K
    11. 75356
    Prev
    Next
    INDEX
    Explanations

    connections between cultural engagement and mental wellbeing

    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
    isku
    -0.08
    bias
    -0.08
    gebn
    -0.07
    Bias
    -0.07
    ignet
    -0.07
     Bias
    -0.07
    ạ
    -0.07
    pdata
    -0.07
    mpar
    -0.07
    hesive
    -0.07
    POSITIVE LOGITS
    ä»ķ
    0.07
     hypo
    0.07
     med
    0.06
     mediation
    0.06
     intermediary
    0.06
     dispos
    0.06
     Specification
    0.06
     link
    0.06
     intermedi
    0.06
     relationship
    0.06
    Activations Density 0.008%

    No Known Activations