© 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. 72797
    Prev
    Next
    INDEX
    Explanations

    titles and positions associated with academic professors and their respective fields

    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
    anca
    -0.07
    ifo
    -0.07
    ighbor
    -0.07
    ivy
    -0.07
    edback
    -0.07
    edl
    -0.07
    edd
    -0.07
    erdem
    -0.07
    gili
    -0.07
    eworld
    -0.07
    POSITIVE LOGITS
    STYPE
    0.06
    âĦ¢
    0.06
     Noon
    0.06
    etto
    0.06
    ickerView
    0.06
     STDERR
    0.06
    lux
    0.06
    ¢åįķ
    0.06
     Hamm
    0.05
    ëıħ
    0.05
    Activations Density 0.005%

    No Known Activations