© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93650
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication patterns and timing in conversations

    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
    .cgi
    -0.07
    adlo
    -0.07
     queda
    -0.07
    enville
    -0.07
    allee
    -0.06
    ιθ
    -0.06
    ordes
    -0.06
     someday
    -0.06
    otte
    -0.06
    kees
    -0.06
    POSITIVE LOGITS
     prior
    0.23
     before
    0.18
    prior
    0.18
     Prior
    0.18
     earlier
    0.18
    Prior
    0.17
     pre
    0.17
     preceding
    0.16
     trÆ°á»Ľc
    0.16
    before
    0.15
    Activations Density 0.183%

    No Known Activations