© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75559
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating differentiation or uniqueness

    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
    dorf
    -0.09
    rief
    -0.08
     Tarif
    -0.08
    insky
    -0.07
    ptime
    -0.07
    ï¼ł
    -0.07
    eah
    -0.07
    bjerg
    -0.07
    /shop
    -0.07
    dın
    -0.07
    POSITIVE LOGITS
     cannot
    0.07
     perhaps
    0.07
    antal
    0.06
    295
    0.06
     simply
    0.06
    pekt
    0.06
     Jen
    0.06
     would
    0.06
     or
    0.06
     failed
    0.06
    Activations Density 0.013%

    No Known Activations