© 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. 9-LLAMASCOPE-RES-131K
    11. 95526
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or motivation

    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
    imed
    -0.06
    iode
    -0.06
     Jog
    -0.06
     Genre
    -0.06
    ture
    -0.06
    ottie
    -0.06
     needy
    -0.06
    ayan
    -0.06
    -0.05
    Å¡ov
    -0.05
    POSITIVE LOGITS
    ä¸įåĪ°
    0.08
    ìĸ¼
    0.07
    angs
    0.07
    اعÙĬ
    0.07
     Äijảo
    0.07
    egie
    0.07
     Daha
    0.07
     NotImplemented
    0.07
    nga
    0.07
    agher
    0.07
    Activations Density 0.007%

    No Known Activations