© 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. 120389
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "announced."

    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
     Ridley
    -0.06
    atif
    -0.06
    /to
    -0.06
    ched
    -0.06
    ussen
    -0.06
    grass
    -0.06
    èIJ½
    -0.06
    ìŀ¬
    -0.06
    hev
    -0.06
    rite
    -0.05
    POSITIVE LOGITS
     plans
    0.12
     Plans
    0.09
    ëĮĢë¡ľ
    0.09
     bahwa
    0.09
    plans
    0.08
    ogui
    0.08
     rằng
    0.08
    endale
    0.08
     that
    0.07
     plan
    0.07
    Activations Density 0.014%

    No Known Activations