© 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. 14740
    Prev
    Next
    INDEX
    Explanations

    the presence of the name "Feldman" in various contexts

    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
    ced
    -0.08
    nun
    -0.07
    ned
    -0.07
    nex
    -0.07
    ÅĻÃŃz
    -0.07
    odyn
    -0.06
    igu
    -0.06
    ëħIJ
    -0.06
    stell
    -0.06
     sobie
    -0.06
    POSITIVE LOGITS
    spar
    0.12
    579
    0.07
    assen
    0.07
    stein
    0.07
    567
    0.07
    574
    0.07
    ẫ
    0.07
    ERVE
    0.07
    taj
    0.06
    eration
    0.06
    Activations Density 0.004%

    No Known Activations