© 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. 98489
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "for" and related legal terminology

    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
    ker
    -0.06
    020
    -0.06
    009
    -0.06
     tours
    -0.06
    akov
    -0.06
    ha
    -0.06
    eh
    -0.05
    è¾ħ
    -0.05
    å±±å¸Ĥ
    -0.05
    ÃŃnh
    -0.05
    POSITIVE LOGITS
    chestra
    0.08
    omik
    0.07
    warz
    0.07
    lopedia
    0.07
     Ging
    0.07
    outu
    0.06
    mada
    0.06
    tura
    0.06
    ushima
    0.06
    itus
    0.06
    Activations Density 0.007%

    No Known Activations