© 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. 117915
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "abstract" and its variations related to abstraction concepts

    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
    )prepare
    -0.08
    ÑĥÑĩа
    -0.08
    packing
    -0.07
    arde
    -0.07
    лик
    -0.06
    одо
    -0.06
    pek
    -0.06
    лив
    -0.06
    /inet
    -0.06
    ynet
    -0.06
    POSITIVE LOGITS
    ed
    0.12
    edly
    0.11
    ively
    0.08
    ti
    0.08
    ivism
    0.08
    /loose
    0.08
    s
    0.07
    ified
    0.07
    ing
    0.07
    ly
    0.07
    Activations Density 0.005%

    No Known Activations