© 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. 87059
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "hang" and its variations

    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
    .appspot
    -0.07
    .codes
    -0.07
    gnu
    -0.06
    PRINTF
    -0.06
    ickle
    -0.06
    uario
    -0.06
     впеÑĢед
    -0.06
    ahead
    -0.06
    òng
    -0.06
    /*/
    -0.06
    POSITIVE LOGITS
     hung
    0.10
     hang
    0.10
     Hang
    0.10
     hanging
    0.10
    over
    0.09
     Hanging
    0.09
    Hang
    0.09
     hangs
    0.09
    hang
    0.07
    rier
    0.07
    Activations Density 0.008%

    No Known Activations