© 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. 61977
    Prev
    Next
    INDEX
    Explanations

    statistical data and numerical values in medical research studies

    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
    zs
    -0.06
    fas
    -0.06
    çĴĥ
    -0.06
    zer
    -0.06
    kas
    -0.06
    ster
    -0.05
    zing
    -0.05
    /board
    -0.05
    :async
    -0.05
    ำ
    -0.05
    POSITIVE LOGITS
    ervo
    0.07
    _WAKE
    0.07
    Mine
    0.07
    ogui
    0.07
    Å¡li
    0.07
    mine
    0.06
    ERT
    0.06
    rote
    0.06
     सप
    0.06
    LayoutParams
    0.06
    Activations Density 0.008%

    No Known Activations