© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57849
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structures, particularly matrices

    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
    ỡ
    -0.07
    reo
    -0.06
    oldt
    -0.06
    -Fi
    -0.06
     SPDX
    -0.06
    abilité
    -0.06
    IRECT
    -0.06
    ocket
    -0.06
     Cumhur
    -0.06
    rng
    -0.06
    POSITIVE LOGITS
     Ezra
    0.06
    .partition
    0.06
    urs
    0.06
    нож
    0.06
    quis
    0.06
    še
    0.06
    大人
    0.06
    ảnh
    0.06
    erness
    0.06
    _PARTITION
    0.06
    Activations Density 0.007%

    No Known Activations