© 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. 120779
    Prev
    Next
    INDEX
    Explanations

    issues related to language learning and proficiency challenges

    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
    adera
    -0.08
    idar
    -0.08
    uale
    -0.07
    vé
    -0.07
    jsc
    -0.07
    readcr
    -0.07
    sel
    -0.07
    arges
    -0.07
    argent
    -0.07
    çļĦæīĭ
    -0.07
    POSITIVE LOGITS
     foreign
    0.08
     foreigners
    0.07
    amb
    0.07
    wright
    0.07
    foreign
    0.07
     sounded
    0.06
    PLICATE
    0.06
     FOREIGN
    0.06
     Foreign
    0.06
     Watson
    0.06
    Activations Density 0.003%

    No Known Activations