© 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. 9-LLAMASCOPE-RES-131K
    11. 97487
    Prev
    Next
    INDEX
    Explanations

    instances of the word "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
    yn
    -0.06
    erg
    -0.06
    ys
    -0.06
    erais
    -0.06
    amp
    -0.06
    lys
    -0.06
    aises
    -0.06
    assel
    -0.06
     degradation
    -0.05
    ally
    -0.05
    POSITIVE LOGITS
    ÑĨо
    0.08
     ÑĩиÑģле
    0.07
    _fence
    0.07
    frauen
    0.07
     tá»Ń
    0.07
    اÙģÙĤ
    0.07
    Ậ
    0.06
    thew
    0.06
    Ú©Ø´
    0.06
    .setAction
    0.06
    Activations Density 0.038%

    No Known Activations