© 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 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. 82951
    Prev
    Next
    INDEX
    Explanations

    various opening and closing angle brackets in markup or code syntax

    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
    regn
    -0.07
    κε
    -0.07
    atis
    -0.07
    cas
    -0.07
    ariant
    -0.07
    rana
    -0.07
    lose
    -0.07
    owy
    -0.06
    anner
    -0.06
    rite
    -0.06
    POSITIVE LOGITS
    èľĺèĽĽè¯į
    0.08
    orama
    0.07
    æ²Ļ
    0.07
    ó
    0.07
     Setter
    0.06
    Setter
    0.06
    i
    0.06
    UNUSED
    0.06
    IDO
    0.06
    ROTO
    0.06
    Activations Density 0.117%

    No Known Activations