© 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. 107415
    Prev
    Next
    INDEX
    Explanations

    phrases indicating addition or inclusion of information

    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
    975
    -0.07
    antha
    -0.07
    ukan
    -0.07
    bose
    -0.07
    baz
    -0.07
     Rip
    -0.06
    .currency
    -0.06
    ÙĬاÙĨ
    -0.06
    :animated
    -0.06
    atch
    -0.06
    POSITIVE LOGITS
    lland
    0.07
     regular
    0.06
    vern
    0.06
    lesai
    0.06
    oland
    0.06
    itia
    0.06
     our
    0.06
    nish
    0.06
     traditional
    0.05
    ONTAL
    0.05
    Activations Density 0.015%

    No Known Activations