© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84593
    Prev
    Next
    INDEX
    Explanations

    phrases related to professionalism and service quality in reviews

    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
    iska
    -0.07
    .habbo
    -0.07
    irl
    -0.07
    queda
    -0.06
     ”
    -0.06
    InProgress
    -0.06
    ushi
    -0.06
    ÑĦоÑĢми
    -0.06
    kowski
    -0.06
    hero
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
    pNet
    0.07
    ëł¥
    0.07
    leich
    0.07
    ãĥ¥ãĥ¼
    0.07
    ENÃį
    0.07
     yyn
    0.07
    à¸Ľà¸£à¸°à¸Īำ
    0.06
    imizer
    0.06
    olik
    0.06
    Activations Density 0.043%

    No Known Activations