© 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 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. 131020
    Prev
    Next
    INDEX
    Explanations

    themes related to honesty and personal values

    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
    swire
    -0.07
    _plural
    -0.06
     Oaks
    -0.06
    otate
    -0.06
    á»ķ
    -0.06
    rss
    -0.06
    <TKey
    -0.06
    Dic
    -0.06
     rss
    -0.06
     hugs
    -0.06
    POSITIVE LOGITS
     profile
    0.09
     PROFILE
    0.08
    /profile
    0.07
    _profile
    0.07
     Profile
    0.07
    edes
    0.07
     bio
    0.06
     description
    0.06
     Bio
    0.06
     Lounge
    0.06
    Activations Density 0.002%

    No Known Activations