© 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. 77146
    Prev
    Next
    INDEX
    Explanations

    specific organizations and causes related to social issues and community support

    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
    plevel
    -0.10
    $MESS
    -0.09
    phans
    -0.09
    pline
    -0.08
    ses
    -0.08
    serrat
    -0.08
    iphery
    -0.08
    ennial
    -0.07
    ensitive
    -0.07
    istor
    -0.07
    POSITIVE LOGITS
    odore
    0.22
    adays
    0.21
    etheless
    0.20
    atre
    0.17
    ÑįÑĤомÑĥ
    0.15
    bsites
    0.13
    xiety
    0.13
    tlement
    0.12
    atomy
    0.12
    gether
    0.12
    Activations Density 0.401%

    No Known Activations