© 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. 15-LLAMASCOPE-RES-131K
    11. 103761
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveys and feedback processes

    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
     Arap
    -0.09
    ãĥ³ãĥIJ
    -0.07
    ereo
    -0.07
    793
    -0.06
     lin
    -0.06
    istrovstvÃŃ
    -0.06
    lý
    -0.06
    htags
    -0.06
    _Meta
    -0.06
     cave
    -0.06
    POSITIVE LOGITS
     surveys
    0.07
     survey
    0.07
     Survey
    0.07
     ips
    0.07
    izza
    0.07
     answers
    0.07
    collector
    0.07
     polls
    0.06
     DefaultValue
    0.06
    gere
    0.06
    Activations Density 0.036%

    No Known Activations