© 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. 5-LLAMASCOPE-RES-131K
    11. 126846
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, primarily semicolons and other trace-related terms

    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
    emmel
    -0.08
    ey
    -0.06
    stdbool
    -0.06
    жÑĥ
    -0.06
    .getChildAt
    -0.06
    erver
    -0.06
    acic
    -0.06
    opoulos
    -0.06
    obby
    -0.06
    ymm
    -0.06
    POSITIVE LOGITS
    liÄŁinde
    0.07
    $MESS
    0.07
     Bast
    0.06
    493
    0.06
     å¾ĴæŃ©
    0.06
    ¢
    0.06
     Natural
    0.06
     ÑĥÑģл
    0.06
    ushima
    0.06
    ÑģÑĤÑĥп
    0.06
    Activations Density 0.001%

    No Known Activations