© 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. 127044
    Prev
    Next
    INDEX
    Explanations

    negative constructions and emotional expressions related to mental health

    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
    ond
    -0.08
    insky
    -0.07
    اذ
    -0.06
    luž
    -0.06
    iae
    -0.06
    imit
    -0.06
    orea
    -0.06
    IRECT
    -0.06
    swire
    -0.06
    431
    -0.06
    POSITIVE LOGITS
    pit
    0.07
     pil
    0.06
     Ñĩем
    0.06
     Rack
    0.06
    noun
    0.06
    ekli
    0.06
    hos
    0.06
    gratis
    0.06
    æĮ¥
    0.06
    ãĥ
    0.06
    Activations Density 0.055%

    No Known Activations