© 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. 93973
    Prev
    Next
    INDEX
    Explanations

    sentiments related to personal 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
    mere
    -0.08
    osta
    -0.08
    /utility
    -0.08
    ntity
    -0.07
    νια
    -0.07
    олева
    -0.07
    лоб
    -0.07
    ãģªãģĮãĤī
    -0.07
    Assignable
    -0.07
    omba
    -0.07
    POSITIVE LOGITS
     even
    0.07
     likewise
    0.06
    ;
    0.06
    anner
    0.06
    elerik
    0.06
     also
    0.05
    rome
    0.05
     Gram
    0.05
     etc
    0.05
     Jud
    0.05
    Activations Density 0.025%

    No Known Activations