© 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. 17-LLAMASCOPE-RES-131K
    11. 124813
    Prev
    Next
    INDEX
    Explanations

    references to copyright

    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
    amac
    -0.06
     Am
    -0.06
     escaping
    -0.06
    [
    -0.06
    arden
    -0.05
    erie
    -0.05
     tr
    -0.05
     /
    -0.05
     Lucky
    -0.05
    864
    -0.05
    POSITIVE LOGITS
    ÅĻez
    0.09
    krom
    0.08
    ilor
    0.08
    ÏģÏİν
    0.08
    intColor
    0.08
    FRINGEMENT
    0.08
    itten
    0.08
    eneg
    0.08
    UCT
    0.07
    aticon
    0.07
    Activations Density 0.008%

    No Known Activations