© 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. 117441
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    á»ijng
    -0.09
    оÑĢоÑĤ
    -0.07
    (Of
    -0.07
    rone
    -0.07
    (.)
    -0.07
    رÙĪس
    -0.07
    opal
    -0.06
    engeance
    -0.06
    μÏĢο
    -0.06
    δί
    -0.06
    POSITIVE LOGITS
    ilha
    0.06
     forever
    0.06
    iler
    0.06
    ag
    0.06
    cassert
    0.06
    ´
    0.06
    ohana
    0.06
     Joh
    0.06
    letal
    0.06
    ´Ī
    0.06
    Activations Density 0.000%

    No Known Activations