© 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 EvalsExportsinterp-engineNEWAPI 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. 30710
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations, particularly those with notable cultural or contextual significance

    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
    éĥİ
    -0.06
    ith
    -0.06
    boats
    -0.06
    .DAL
    -0.06
    pell
    -0.06
    adel
    -0.06
    icate
    -0.06
    AZY
    -0.06
    aler
    -0.06
    fty
    -0.06
    POSITIVE LOGITS
    /OR
    0.10
    ektor
    0.07
    LLL
    0.07
    Ð®ÐĽ
    0.07
    -Identifier
    0.07
    lenen
    0.07
    _EDEFAULT
    0.07
    esion
    0.07
    бÑĥдÑĮ
    0.07
    ego
    0.06
    Activations Density 0.217%

    No Known Activations