© 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. 9-LLAMASCOPE-RES-131K
    11. 97354
    Prev
    Next
    INDEX
    Explanations

    mentions of specific colleges and universities

    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
    .esp
    -0.07
    å§Ķ
    -0.07
    rav
    -0.07
    cord
    -0.07
    amina
    -0.07
    еÑĢеж
    -0.07
     kav
    -0.06
    iring
    -0.06
    orce
    -0.06
    ços
    -0.06
    POSITIVE LOGITS
    Ħ
    0.07
    sing
    0.06
    borough
    0.06
    zig
    0.06
    again
    0.06
     again
    0.06
     circulation
    0.06
     Cru
    0.06
     sing
    0.06
    517
    0.05
    Activations Density 0.267%

    No Known Activations