© 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. 96267
    Prev
    Next
    INDEX
    Explanations

    assertions and testing functionality in code

    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
    apter
    -0.07
    yme
    -0.07
    olan
    -0.06
    aj
    -0.06
    slides
    -0.06
    ansi
    -0.06
    fad
    -0.06
    érc
    -0.06
    agar
    -0.06
    agini
    -0.06
    POSITIVE LOGITS
    idon
    0.08
    ìĹ°
    0.07
    gings
    0.07
    ابد
    0.07
    jeme
    0.06
    nop
    0.06
    Holder
    0.06
    .(*
    0.06
    asel
    0.06
    ãģ¹
    0.06
    Activations Density 0.001%

    No Known Activations