© 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. 96263
    Prev
    Next
    INDEX
    Explanations

    occurrences of quotation marks and other punctuation that indicate speech or titles

    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
    ener
    -0.06
    ery
    -0.06
    f
    -0.06
    umber
    -0.06
    ilar
    -0.05
    9
    -0.05
    king
    -0.05
     Král
    -0.05
    906
    -0.05
    ler
    -0.05
    POSITIVE LOGITS
    знаÑĩа
    0.08
    rve
    0.07
    implify
    0.07
    znam
    0.07
    olib
    0.07
    ê°Ļ
    0.07
    ucken
    0.07
    rray
    0.07
    elige
    0.07
    createFrom
    0.07
    Activations Density 0.022%

    No Known Activations