© 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. 3778
    Prev
    Next
    INDEX
    Explanations

    references to artistic expression and the actions involved in creation

    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
    æķ
    -0.07
    баÑĩ
    -0.06
    CV
    -0.06
    emek
    -0.06
    ilio
    -0.06
    sert
    -0.06
    εια
    -0.06
     wyst
    -0.06
    ìħĶ
    -0.06
    件
    -0.06
    POSITIVE LOGITS
     done
    0.10
     doing
    0.10
    Doing
    0.09
     Doing
    0.08
    doing
    0.08
     Done
    0.07
    åģļ
    0.07
    _done
    0.07
    done
    0.07
     did
    0.07
    Activations Density 0.018%

    No Known Activations