© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95070
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups of people

    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
     itself
    -0.07
    ly
    -0.06
    729
    -0.06
    INLINE
    -0.06
    wnd
    -0.06
    icle
    -0.06
    wy
    -0.06
     tol
    -0.06
    ÌĢ
    -0.06
    eming
    -0.06
    POSITIVE LOGITS
    ÏĦÏĮ
    0.07
    /DD
    0.07
    .synthetic
    0.07
    .il
    0.07
    /from
    0.07
    Äįet
    0.06
    /her
    0.06
    .vaadin
    0.06
    CursorPosition
    0.06
    /us
    0.06
    Activations Density 0.025%

    No Known Activations