Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56180
    Prev
    Next
    INDEX
    Explanations

    phrases related to cultural events and tourism

    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
    uur
    -0.06
     aids
    -0.06
    .cc
    -0.06
     aid
    -0.06
    ÙĨØ´
    -0.06
    aid
    -0.06
     Needle
    -0.06
    ParameterValue
    -0.05
     Mens
    -0.05
    oriously
    -0.05
    POSITIVE LOGITS
    pth
    0.07
    ÑĥÑĩа
    0.07
    spell
    0.07
    åŀ
    0.06
     Campus
    0.06
    æĬĺ
    0.06
    .mixin
    0.06
    åħ¼
    0.06
    omal
    0.06
    itou
    0.06
    Activations Density 0.004%

    No Known Activations