© 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. 55374
    Prev
    Next
    INDEX
    Explanations

    HTML list elements and their attributes

    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
    fur
    -0.07
    ihan
    -0.06
    aign
    -0.06
    ouch
    -0.06
    iku
    -0.06
    addin
    -0.06
    hawk
    -0.06
    ÑĥÑĪ
    -0.06
     helf
    -0.06
    ä¾µ
    -0.06
    POSITIVE LOGITS
    vers
    0.07
     fingert
    0.06
    acc
    0.06
    slu
    0.06
    OfClass
    0.06
    Merc
    0.06
    WebResponse
    0.06
    871
    0.06
    ossil
    0.06
    adt
    0.06
    Activations Density 0.002%

    No Known Activations