© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 107127
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs associated with questioning and seeking information

    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
    Ëĺ
    -0.06
    Į¨
    -0.06
    annah
    -0.06
    ahun
    -0.06
    LOPT
    -0.06
    \Annotation
    -0.06
    bull
    -0.06
    ázi
    -0.06
    alah
    -0.06
    _sdk
    -0.06
    POSITIVE LOGITS
     exactly
    0.07
    IAS
    0.07
    apsed
    0.07
     prefer
    0.07
    kea
    0.06
     Prefer
    0.06
    èĬ³
    0.06
    ends
    0.06
    traction
    0.06
    еÑĢк
    0.06
    Activations Density 0.027%

    No Known Activations