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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 124549
    Prev
    Next
    INDEX
    Explanations

    commas used in lists or to separate items

    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
    a
    -0.06
    uu
    -0.06
     penn
    -0.06
     Ai
    -0.05
     base
    -0.05
    å¢Ĺ
    -0.05
    BUFFER
    -0.05
    宿
    -0.05
     @
    -0.05
     an
    -0.05
    POSITIVE LOGITS
    #ac
    0.08
    éļĨ
    0.08
    ãģıãģł
    0.08
    USA
    0.07
    iban
    0.07
    é¼
    0.07
    Touches
    0.07
    à¥Ģà¤Ĺ
    0.07
    ibold
    0.07
    luž
    0.07
    Activations Density 0.004%

    No Known Activations