© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125455
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wade" and its variations, often in contexts involving navigating through a challenging situation

    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
     overhead
    -0.07
    pent
    -0.06
    emale
    -0.06
     runaway
    -0.06
    thag
    -0.06
    xdb
    -0.06
    aml
    -0.06
    imum
    -0.06
    secutive
    -0.06
    antom
    -0.06
    POSITIVE LOGITS
    ModelError
    0.07
    ermalink
    0.07
    hr
    0.07
    ÑĥÑĢи
    0.07
    leyen
    0.07
    kits
    0.07
    iggins
    0.06
    ãĥ¼ãĥ©
    0.06
    аÑĢÑħ
    0.06
    Normals
    0.06
    Activations Density 0.002%

    No Known Activations