© 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. 126818
    Prev
    Next
    INDEX
    Explanations

    instances of questioning or inquiries about various topics

    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
    ications
    -0.07
    allet
    -0.07
    unga
    -0.07
    егоÑĢ
    -0.07
    ucken
    -0.06
    aye
    -0.06
    orre
    -0.06
    ald
    -0.06
    lh
    -0.06
     Pru
    -0.06
    POSITIVE LOGITS
     whether
    0.13
     Whether
    0.10
    /question
    0.10
    whether
    0.10
    Whether
    0.10
    æĺ¯åIJ¦
    0.10
     why
    0.08
     WHETHER
    0.08
    naires
    0.08
     æĺ¯åIJ¦
    0.08
    Activations Density 0.008%

    No Known Activations