© 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. 94455
    Prev
    Next
    INDEX
    Explanations

    identifiers related to programming or data types

    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
    indow
    -0.08
    bru
    -0.07
    plode
    -0.07
    sez
    -0.07
    raison
    -0.07
    ocator
    -0.07
    coon
    -0.07
    _NT
    -0.07
    _AI
    -0.06
     aray
    -0.06
    POSITIVE LOGITS
     vicinity
    0.07
    b
    0.07
    apa
    0.06
    ĩ
    0.06
    315
    0.05
    ingham
    0.05
    Dll
    0.05
    ستÛĮ
    0.05
    lund
    0.05
    usters
    0.05
    Activations Density 0.028%

    No Known Activations