© 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. 78166
    Prev
    Next
    INDEX
    Explanations

    references to cultural institutions and their exhibits

    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
    enburg
    -0.10
    eniz
    -0.08
    ëĬ¥
    -0.08
    본
    -0.08
    TRS
    -0.08
    ISR
    -0.08
    çŃĨ
    -0.08
    Transmission
    -0.07
    engeance
    -0.07
     عز
    -0.07
    POSITIVE LOGITS
     life
    0.08
     history
    0.08
     evolution
    0.08
     local
    0.07
     role
    0.07
     past
    0.07
     disp
    0.07
     themes
    0.07
     roles
    0.06
    ax
    0.06
    Activations Density 0.017%

    No Known Activations