© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75801
    Prev
    Next
    INDEX
    Explanations

    elements related to book releases and literary events

    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
    ALER
    -0.07
    izzo
    -0.07
    aka
    -0.07
    enna
    -0.07
    .GridView
    -0.06
    .TestTools
    -0.06
    ilyn
    -0.06
    OLVE
    -0.06
    bounce
    -0.06
    engu
    -0.06
    POSITIVE LOGITS
    unker
    0.07
     Novel
    0.07
    turnstile
    0.07
     novel
    0.07
    intros
    0.06
     Experimental
    0.06
    åĭ
    0.06
     literary
    0.06
    /logging
    0.06
    WSC
    0.06
    Activations Density 0.005%

    No Known Activations