© 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. 95274
    Prev
    Next
    INDEX
    Explanations

    terms related to consumer behavior and consumption

    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
    ific
    -0.08
    ement
    -0.08
    ifik
    -0.07
    lef
    -0.07
    uber
    -0.07
    castle
    -0.07
    zes
    -0.07
    odes
    -0.07
    dings
    -0.07
    acey
    -0.06
    POSITIVE LOGITS
    ption
    0.11
    ptions
    0.08
    PTION
    0.08
    ables
    0.08
    neau
    0.07
    jon
    0.07
    èĢħçļĦ
    0.07
    ptive
    0.07
    èĢħ
    0.07
    267
    0.07
    Activations Density 0.018%

    No Known Activations