© 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 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. 16374
    Prev
    Next
    INDEX
    Explanations

    keywords related to roofing and flooring materials and services

    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
    ayah
    -0.08
    REATED
    -0.08
    arshal
    -0.08
    ÙĦÛĮسÛĮ
    -0.08
    fone
    -0.07
    uitka
    -0.07
    ATUS
    -0.07
    .Flow
    -0.07
    lege
    -0.07
    elsing
    -0.07
    POSITIVE LOGITS
     assim
    0.06
     Gent
    0.06
     ans
    0.06
    -
    0.06
     voc
    0.06
    tx
    0.05
    uv
    0.05
     innov
    0.05
     inter
    0.05
     kinds
    0.05
    Activations Density 0.000%

    No Known Activations