© 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. 83708
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    วรรà¸ĵ
    -0.07
    ãĤ¾
    -0.07
    weigh
    -0.07
    Å¡ek
    -0.07
     èĹ
    -0.07
    егоÑĢ
    -0.07
    cret
    -0.07
    ocale
    -0.06
    /Instruction
    -0.06
    ãĥ¼ãĥij
    -0.06
    POSITIVE LOGITS
     dep
    0.08
    atty
    0.06
    asar
    0.06
     arity
    0.06
    intval
    0.06
     odd
    0.06
    ERICA
    0.06
    éis
    0.06
    arty
    0.05
     Soul
    0.05
    Activations Density 0.061%

    No Known Activations