© 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. 123638
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "school" and its variations

    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
    rias
    -0.06
    lech
    -0.06
    è·¡
    -0.06
    ul
    -0.05
    NING
    -0.05
    HIR
    -0.05
    or
    -0.05
    793
    -0.05
    ud
    -0.05
    ycz
    -0.05
    POSITIVE LOGITS
    -wide
    0.08
    icular
    0.08
    yard
    0.08
    wide
    0.08
    .joda
    0.08
    éĹ
    0.07
    mates
    0.07
    mate
    0.07
    imenti
    0.07
    ekler
    0.07
    Activations Density 0.015%

    No Known Activations