© 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. 17-LLAMASCOPE-RES-131K
    11. 59909
    Prev
    Next
    INDEX
    Explanations

    references to influential figures and their impact on society or culture

    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
    ilon
    -0.06
    輪
    -0.06
    yet
    -0.06
     both
    -0.06
    Äįást
    -0.06
    _BOTH
    -0.05
     Everyone
    -0.05
     Winston
    -0.05
     wire
    -0.05
     everyone
    -0.05
    POSITIVE LOGITS
     any
    0.24
     ANY
    0.21
    any
    0.19
    ä»»ä½ķ
    0.17
     qualquer
    0.17
     anywhere
    0.16
    (any
    0.16
     cualquier
    0.16
    ANY
    0.15
    Any
    0.15
    Activations Density 0.069%

    No Known Activations