© 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. 18446
    Prev
    Next
    INDEX
    Explanations

    terms indicating roles or functions held by individuals

    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
    amarin
    -0.09
     bang
    -0.07
    ataire
    -0.07
    éal
    -0.07
    atile
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    ainter
    -0.07
    bang
    -0.07
    HK
    -0.07
    oft
    -0.07
    POSITIVE LOGITS
    ech
    0.06
    alus
    0.06
    640
    0.06
    ãĤĵãģ©
    0.06
    åĿĬ
    0.06
    -TV
    0.06
    nel
    0.06
    ole
    0.05
    å¿Ĺ
    0.05
    642
    0.05
    Activations Density 0.008%

    No Known Activations