© 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. 106230
    Prev
    Next
    INDEX
    Explanations

    elements related to data storage and organization

    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
    enate
    -0.06
     Lucas
    -0.06
    iland
    -0.06
    _locals
    -0.06
    алÑİ
    -0.06
     Saw
    -0.06
    agle
    -0.06
    las
    -0.06
     Sanayi
    -0.06
     Gree
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
    senal
    0.07
    odos
    0.07
    NSNotification
    0.07
    angstrom
    0.07
    410
    0.06
    CLUDED
    0.06
    uhl
    0.06
     Propel
    0.06
    ä½³
    0.06
    Activations Density 0.012%

    No Known Activations