© 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. 15-LLAMASCOPE-RES-131K
    11. 87297
    Prev
    Next
    INDEX
    Explanations

    references to hot dogs in discussions about food classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text discussing whether something can or should be categorized or classified within a particular group, often showing uncertainty or debate about classification status.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    erdale
    -0.06
    angl
    -0.06
    udder
    -0.06
     kond
    -0.06
    ¥
    -0.06
    ÏĢοÏį
    -0.06
     GetLastError
    -0.06
    angen
    -0.06
    arden
    -0.06
    andin
    -0.06
    POSITIVE LOGITS
     definition
    0.08
    -definition
    0.07
     definitions
    0.07
    term
    0.07
    <decltype
    0.07
     label
    0.07
     Definition
    0.07
    buz
    0.06
     officially
    0.06
    official
    0.06
    Activations Density 0.160%

    No Known Activations