© 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. 118473
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional connection and nostalgia

    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
    .Persistence
    -0.06
     committed
    -0.06
    ardware
    -0.06
    亮
    -0.06
    ç§Ģ
    -0.06
     Magnet
    -0.05
     widest
    -0.05
     æĢ§
    -0.05
    æĢ§
    -0.05
    istry
    -0.05
    POSITIVE LOGITS
     feelings
    0.16
     feeling
    0.16
     Feel
    0.13
     felt
    0.13
     feel
    0.13
    Feel
    0.12
     feels
    0.12
    feel
    0.11
     Feeling
    0.11
     sensation
    0.11
    Activations Density 0.080%

    No Known Activations