© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95795
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers and references related to books

    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
    tor
    -0.07
    cape
    -0.06
    /libs
    -0.06
    sex
    -0.05
    .gdx
    -0.05
    hill
    -0.05
     Identity
    -0.05
     screw
    -0.05
     (
    -0.05
    420
    -0.05
    POSITIVE LOGITS
    ulings
    0.08
    hoa
    0.07
    vod
    0.07
     íĭ
    0.07
    лика
    0.07
     *__
    0.07
     mos
    0.07
    -INF
    0.07
    ISCO
    0.07
    anken
    0.07
    Activations Density 0.004%

    No Known Activations