© 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. 85650
    Prev
    Next
    INDEX
    Explanations

    plural possessive forms and contractions

    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
    digest
    -0.07
    cac
    -0.07
    Quest
    -0.07
    .GPIO
    -0.07
    lesh
    -0.07
    dump
    -0.06
    [email
    -0.06
    lif
    -0.06
    vů
    -0.06
    лÑĥг
    -0.06
    POSITIVE LOGITS
    Ø¡
    0.07
    beh
    0.06
     Dos
    0.06
    639
    0.06
    getList
    0.06
    ÂŁ
    0.06
    egral
    0.06
    ikt
    0.06
    Dos
    0.06
    wner
    0.06
    Activations Density 0.002%

    No Known Activations