© 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. 15522
    Prev
    Next
    INDEX
    Explanations

    phrases related to qualifications and suitability for roles or tasks

    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
    ksi
    -0.07
    anko
    -0.07
    laus
    -0.07
    UBE
    -0.07
    ãng
    -0.07
    ież
    -0.07
    alta
    -0.07
     Incontri
    -0.07
    asley
    -0.07
    (æĹ¥
    -0.07
    POSITIVE LOGITS
    /lic
    0.08
    ness
    0.07
    /legal
    0.06
     Lid
    0.06
     persons
    0.06
     to
    0.06
    /auth
    0.05
    èĴĻ
    0.05
    icit
    0.05
     Persons
    0.05
    Activations Density 0.006%

    No Known Activations