© 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. 79520
    Prev
    Next
    INDEX
    Explanations

    comparative terms related to quantity or amount

    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
    èo
    -0.07
    illes
    -0.07
     Tel
    -0.07
    odom
    -0.07
    sic
    -0.07
    vfs
    -0.07
    esser
    -0.06
    èĮ
    -0.06
    ialized
    -0.06
    Tel
    -0.06
    POSITIVE LOGITS
     than
    0.09
    _than
    0.07
    -than
    0.07
    erset
    0.07
     Hart
    0.07
    than
    0.06
    ilha
    0.06
    ertainment
    0.06
    errat
    0.06
     sayıda
    0.06
    Activations Density 0.024%

    No Known Activations