© 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. 79407
    Prev
    Next
    INDEX
    Explanations

    academic titles and positions associated with prestigious institutions

    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
    ınca
    -0.07
    į
    -0.06
    Ãło
    -0.06
    ÑĥзÑĭ
    -0.06
    uhan
    -0.06
    neau
    -0.06
    zew
    -0.06
     Sexo
    -0.06
    ziehung
    -0.06
    mmc
    -0.06
    POSITIVE LOGITS
     Chair
    0.10
     chair
    0.10
     Professor
    0.09
     Lect
    0.09
     professor
    0.09
    Chair
    0.08
    chair
    0.08
    Professor
    0.08
     lectures
    0.08
     End
    0.07
    Activations Density 0.104%

    No Known Activations