© 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 EvalsExportsinterp-engineNEWAPI 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. 105378
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Ha" in different contexts, likely indicating humor or laughter

    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
     заб
    -0.06
    centage
    -0.06
    amente
    -0.06
    175
    -0.06
    ersistent
    -0.06
    940
    -0.06
    orb
    -0.06
    457
    -0.06
    illiseconds
    -0.06
    hec
    -0.06
    POSITIVE LOGITS
    uteur
    0.07
    outil
    0.07
    antas
    0.07
    dle
    0.07
    ارک
    0.07
    ÑĦек
    0.07
    PIO
    0.07
    aland
    0.07
    álo
    0.07
    acked
    0.06
    Activations Density 0.009%

    No Known Activations