© 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. 15-LLAMASCOPE-RES-131K
    11. 103335
    Prev
    Next
    INDEX
    Explanations

    paths, directions, and transitions within a physical space

    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
    ãģıãģł
    -0.08
    andes
    -0.07
    zos
    -0.07
    intl
    -0.06
    ени
    -0.06
     ABD
    -0.06
    LM
    -0.06
    APA
    -0.06
    %E
    -0.06
    ansi
    -0.06
    POSITIVE LOGITS
    uyá»ĩt
    0.07
     Serialized
    0.06
    ifter
    0.06
    514
    0.06
     continent
    0.06
    &E
    0.06
    .jdesktop
    0.06
    rans
    0.06
    GLOSS
    0.06
    /from
    0.06
    Activations Density 0.013%

    No Known Activations