© 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. 87327
    Prev
    Next
    INDEX
    Explanations

    pronouns and their connection to health status

    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
    çľģ
    -0.07
    åĢĻ
    -0.07
    ean
    -0.06
    pesan
    -0.06
    سÙĩ
    -0.06
    è¦
    -0.06
    _extensions
    -0.06
    eph
    -0.06
    tout
    -0.06
    sphere
    -0.06
    POSITIVE LOGITS
     condition
    0.07
     situation
    0.07
     symptoms
    0.07
    ORB
    0.06
    agit
    0.06
    ruba
    0.06
    æŁĦ
    0.06
    ailed
    0.06
    _flutter
    0.06
    æ³ģ
    0.06
    Activations Density 0.015%

    No Known Activations