© 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. 80367
    Prev
    Next
    INDEX
    Explanations

    instances of past tense or passive voice

    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
    ane
    -0.06
    ctxt
    -0.06
    gh
    -0.06
    ArgumentException
    -0.06
    (AP
    -0.06
    240
    -0.05
     southwestern
    -0.05
    ÑĪов
    -0.05
    asper
    -0.05
     jet
    -0.05
    POSITIVE LOGITS
    iller
    0.08
    //{{
    0.07
    unsch
    0.07
    iliz
    0.07
    #ab
    0.07
    VED
    0.07
    theid
    0.07
    ÑĢÑĥÑĩ
    0.07
    ewidth
    0.07
    鸡
    0.07
    Activations Density 0.000%

    No Known Activations