© 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. 57711
    Prev
    Next
    INDEX
    Explanations

    concepts related to genetic similarities and organization

    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
    èŀį
    -0.07
    ικο
    -0.07
    ìŀIJìĿ¸
    -0.06
    oux
    -0.06
    ale
    -0.06
    agua
    -0.06
    ble
    -0.06
    sgi
    -0.06
    flt
    -0.06
     åıĮ
    -0.06
    POSITIVE LOGITS
     group
    0.13
     grouping
    0.13
    group
    0.12
    .group
    0.12
     groupName
    0.11
    ãģ¾ãģ¨
    0.11
     Group
    0.11
     together
    0.11
     GROUP
    0.10
     grouped
    0.10
    Activations Density 0.172%

    No Known Activations