© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 93905
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and structures

    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
    ses
    -0.09
    @nate
    -0.07
    rael
    -0.07
    ients
    -0.07
    eer
    -0.07
     (
    -0.07
    phans
    -0.06
    ãĤ§
    -0.06
    cribe
    -0.06
    auc
    -0.06
    POSITIVE LOGITS
    adays
    0.14
    oret
    0.14
    oretical
    0.12
    gether
    0.12
    etheless
    0.11
    atre
    0.11
    bidden
    0.10
    ÑįÑĤомÑĥ
    0.09
    west
    0.09
    xiety
    0.09
    Activations Density 0.174%

    No Known Activations