© 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. 75756
    Prev
    Next
    INDEX
    Explanations

    code elements related to file inclusion and library dependencies

    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
    arga
    -0.08
    meni
    -0.08
    argon
    -0.07
    agues
    -0.07
    igon
    -0.07
    /libs
    -0.07
    li
    -0.07
    elm
    -0.07
    обÑĢаÐ
    -0.06
    ısıt
    -0.06
    POSITIVE LOGITS
     WARRANT
    0.07
    iqueta
    0.06
    _SYS
    0.06
    ãĥĨãĥ«
    0.05
    SERVER
    0.05
     Fior
    0.05
    è¾ĥ
    0.05
    Ĥ
    0.05
    Ù
    0.05
    isky
    0.05
    Activations Density 0.000%

    No Known Activations