© 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. 15-LLAMASCOPE-RES-131K
    11. 1041
    Prev
    Next
    INDEX
    Explanations

    references to video games

    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
    MPI
    -0.07
    éį
    -0.07
    itest
    -0.07
    ازÙħ
    -0.06
    IFS
    -0.06
     floppy
    -0.06
     avent
    -0.06
    ingham
    -0.06
    .Management
    -0.06
    agedList
    -0.06
    POSITIVE LOGITS
    anje
    0.07
    icus
    0.07
    kaar
    0.06
    aney
    0.06
    wnd
    0.06
    leftright
    0.06
    XHR
    0.06
    èĪĪ
    0.06
    892
    0.06
    chants
    0.05
    Activations Density 0.000%

    No Known Activations