© 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. 71352
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and"

    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
    eyi
    -0.08
    ey
    -0.07
    ogra
    -0.07
    تر
    -0.07
    ÑĤик
    -0.06
     respectively
    -0.06
    ÑĤÑĮ
    -0.06
     ÑĢок
    -0.06
    .DropDown
    -0.06
    agara
    -0.06
    POSITIVE LOGITS
     mystical
    0.07
     миÑģÑĤ
    0.06
    casts
    0.06
    arbeit
    0.06
     Foreign
    0.06
     ç¨
    0.06
     FOREIGN
    0.06
     Waters
    0.06
     mastur
    0.06
    иÑģÑĤÑĢа
    0.06
    Activations Density 0.000%

    No Known Activations