© 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. 84634
    Prev
    Next
    INDEX
    Explanations

    references to emotional vulnerability and identity

    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
    šem
    -0.07
    ÑĮеÑĢ
    -0.07
     vur
    -0.07
    unate
    -0.06
    _tip
    -0.06
     DataColumn
    -0.06
    immer
    -0.06
     ”↵↵
    -0.06
     eldre
    -0.06
    \Collections
    -0.06
    POSITIVE LOGITS
     etc
    0.20
    etc
    0.16
     ÑĤоÑīо
    0.11
    çŃī
    0.09
    tc
    0.09
    ãģĿãģĹãģ¦
    0.08
     maybe
    0.08
    /etc
    0.08
    ãģªãģ©
    0.08
     ëĵ±ìĿĦ
    0.07
    Activations Density 0.049%

    No Known Activations