© 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. 61316
    Prev
    Next
    INDEX
    Explanations

    phrases indicating identity and self-reference

    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
    idor
    -0.08
     bidi
    -0.07
    rob
    -0.06
    ippi
    -0.06
    iste
    -0.06
    oh
    -0.06
    chie
    -0.06
    endar
    -0.06
    rip
    -0.06
    olar
    -0.06
    POSITIVE LOGITS
    ÅĻÃŃt
    0.07
    å±Ģ
    0.06
    айÑĤ
    0.06
    ãĥĨãĥ«
    0.06
     luck
    0.06
     sir
    0.06
    yd
    0.06
     welcome
    0.06
     Welcome
    0.06
    aylight
    0.06
    Activations Density 0.013%

    No Known Activations