© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126495
    Prev
    Next
    INDEX
    Explanations

    words related to immediacy and urgency

    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
    anness
    -0.07
    tin
    -0.07
    illez
    -0.06
    itchens
    -0.06
    ØŃÙĨ
    -0.06
    /shop
    -0.06
    ÅĽli
    -0.06
     pitched
    -0.06
    ANTLR
    -0.06
    bole
    -0.06
    POSITIVE LOGITS
     aliqua
    0.07
    enco
    0.07
    era
    0.07
    emd
    0.06
    rek
    0.06
    StartPosition
    0.06
    pts
    0.06
    PTS
    0.06
    izzle
    0.06
    kup
    0.06
    Activations Density 0.019%

    No Known Activations