© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41057
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of media and mediums of expression

    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
    ment
    -0.08
    arend
    -0.07
    OrCreate
    -0.07
    aren
    -0.07
    awai
    -0.07
    arro
    -0.07
    GS
    -0.07
    /todo
    -0.07
    itude
    -0.07
    avid
    -0.07
    POSITIVE LOGITS
    ities
    0.08
    ogy
    0.07
    ately
    0.07
    Ļ
    0.06
    éĹ´
    0.06
    812
    0.06
    nuts
    0.06
    ship
    0.06
    753
    0.06
    linik
    0.06
    Activations Density 0.018%

    No Known Activations