© 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. 98363
    Prev
    Next
    INDEX
    Explanations

    names of people associated with high-profile events or achievements

    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
    ABCDEFGHI
    -0.07
    ABCDEFGHIJKLMNOP
    -0.07
     Lage
    -0.07
    -dismissible
    -0.07
    OptionPane
    -0.07
    ãĥģãĥ¥
    -0.07
    گذ
    -0.07
    KHTML
    -0.07
    uddle
    -0.06
    dG
    -0.06
    POSITIVE LOGITS
     Hub
    0.07
    ukes
    0.06
    888
    0.06
     Davies
    0.06
     Humph
    0.06
    ãĤ¤ãĤ¯
    0.06
    å¶
    0.06
    -deals
    0.05
    479
    0.05
    asje
    0.05
    Activations Density 0.105%

    No Known Activations