© 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. 59050
    Prev
    Next
    INDEX
    Explanations

    code formatting and text manipulation patterns

    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
    isel
    -0.08
    acas
    -0.08
    еÑģи
    -0.07
    isle
    -0.07
    .decorate
    -0.07
    elman
    -0.07
    >}</
    -0.07
    ceae
    -0.07
    cased
    -0.07
    ÑģÑİ
    -0.07
    POSITIVE LOGITS
     replacement
    0.07
     replaced
    0.07
     replace
    0.07
    520
    0.06
     replaces
    0.06
     substitutes
    0.06
    iceps
    0.06
     something
    0.06
     Em
    0.06
     REPLACE
    0.06
    Activations Density 0.011%

    No Known Activations