© 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. 15-LLAMASCOPE-RES-131K
    11. 103548
    Prev
    Next
    INDEX
    Explanations

    physical interactions and placements between characters

    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
    esty
    -0.07
    estic
    -0.07
    unbind
    -0.07
    иплом
    -0.07
    SEM
    -0.07
    åIJĽ
    -0.07
     तल
    -0.07
    ató
    -0.06
    iry
    -0.06
    AdapterFactory
    -0.06
    POSITIVE LOGITS
    Å©i
    0.07
     Tent
    0.06
    ãģ¾ãģ¾
    0.06
     the
    0.06
     Unt
    0.06
    ongs
    0.06
    708
    0.06
    boost
    0.05
     Mass
    0.05
    *log
    0.05
    Activations Density 0.020%

    No Known Activations