© 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. 9-LLAMASCOPE-RES-131K
    11. 97747
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive forms in the text

    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
    ucci
    -0.06
    afi
    -0.06
    Sad
    -0.06
    สล
    -0.06
    itin
    -0.06
    adays
    -0.06
    жен
    -0.06
    械
    -0.06
    лÑĥг
    -0.06
    stav
    -0.06
    POSITIVE LOGITS
    elper
    0.07
    LEN
    0.06
    redits
    0.06
    Ĥæķ°
    0.06
     alike
    0.06
    reck
    0.06
    witter
    0.06
    sis
    0.06
    zyst
    0.06
    RSS
    0.06
    Activations Density 0.091%

    No Known Activations