© 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. 85065
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or structures indicating superiority or difference

    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
    çī
    -0.08
    rani
    -0.07
    -Ñħ
    -0.07
    éłĨ
    -0.07
    ilon
    -0.07
    .seed
    -0.07
     Sink
    -0.07
    ieten
    -0.07
    rello
    -0.06
    ÑĢониÑĩеÑģ
    -0.06
    POSITIVE LOGITS
    isma
    0.07
     perhaps
    0.07
     exists
    0.06
    seen
    0.06
    mere
    0.06
    HEMA
    0.06
     existed
    0.06
     bef
    0.06
    atar
    0.06
    uss
    0.06
    Activations Density 0.022%

    No Known Activations