© 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. 104258
    Prev
    Next
    INDEX
    Explanations

    URLs and domain names associated with website addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Domain extensions and email address components appearing in online citations and contact information.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    219
    -0.07
    kiye
    -0.06
    path
    -0.06
    Ïĥμ
    -0.06
    pose
    -0.06
    ahun
    -0.06
    241
    -0.06
    ẻ
    -0.06
    LC
    -0.06
    _BP
    -0.06
    POSITIVE LOGITS
    bsub
    0.08
    Uvs
    0.07
    GuidId
    0.07
    rzy
    0.07
    .xz
    0.07
    ÑģпÑĸлÑĮ
    0.07
    ogi
    0.07
    sted
    0.06
    ιÏİ
    0.06
    aign
    0.06
    Activations Density 0.001%

    No Known Activations