© 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. 77776
    Prev
    Next
    INDEX
    Explanations

    words and phrases that reference groups of people in an informal or casual context

    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
    reur
    -0.07
    usercontent
    -0.07
    PathComponent
    -0.07
    thon
    -0.07
    ulfilled
    -0.06
    еком
    -0.06
    çģŃ
    -0.06
    .Inject
    -0.06
     лов
    -0.06
    eb
    -0.06
    POSITIVE LOGITS
    itter
    0.07
    chaft
    0.06
    immel
    0.06
    ace
    0.06
    ush
    0.06
     Strap
    0.05
     Por
    0.05
     basic
    0.05
     shock
    0.05
     vest
    0.05
    Activations Density 0.007%

    No Known Activations