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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 124757
    Prev
    Next
    INDEX
    Explanations

    references to openness and receptiveness to new experiences or ideas

    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
    onga
    -0.07
    emin
    -0.07
    olla
    -0.06
    Ùħار
    -0.06
    jak
    -0.06
    å¦ĥ
    -0.06
    nero
    -0.06
    alo
    -0.06
    nameof
    -0.06
    imos
    -0.06
    POSITIVE LOGITS
    -open
    0.10
    å¼ĢæĶ¾
    0.09
    /open
    0.08
     open
    0.08
    Open
    0.08
    OPEN
    0.08
    _open
    0.07
    open
    0.07
     openness
    0.07
     accepting
    0.07
    Activations Density 0.014%

    No Known Activations