© 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. 4051
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or steps involved in a recipe

    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
    ôle
    -0.07
    inoa
    -0.07
    ór
    -0.07
    endez
    -0.06
    altet
    -0.06
    ands
    -0.06
    andal
    -0.06
    anded
    -0.06
    iona
    -0.06
    森
    -0.06
    POSITIVE LOGITS
     hy
    0.06
    ellan
    0.06
    éIJĺ
    0.06
    lope
    0.06
    âĹĨ
    0.06
    ãĤ¶ãĥ¼
    0.05
     deduct
    0.05
     Nem
    0.05
    .Paint
    0.05
    yntax
    0.05
    Activations Density 0.017%

    No Known Activations