© 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. 84027
    Prev
    Next
    INDEX
    Explanations

    phrases related to individual experiences and personal accounts

    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
    itus
    -0.06
    illon
    -0.06
    'gc
    -0.06
    dess
    -0.06
    urn
    -0.06
    opsy
    -0.06
     ãģĿãģ®ä»ĸ
    -0.06
    "urls
    -0.06
    ais
    -0.06
    urses
    -0.06
    POSITIVE LOGITS
     напÑĢимеÑĢ
    0.08
     napÅĻÃŃklad
    0.08
     ÙħØ«ÙĦا
    0.07
    ä¾ĭå¦Ĥ
    0.07
    453
    0.07
    #region
    0.06
    ads
    0.06
     напÑĢиклад
    0.06
    chie
    0.06
     obvious
    0.06
    Activations Density 0.105%

    No Known Activations