© 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. 81137
    Prev
    Next
    INDEX
    Explanations

    references to universities and law schools

    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
    stance
    -0.07
     career
    -0.07
    елов
    -0.06
    ifton
    -0.06
    uning
    -0.06
    inho
    -0.06
    uess
    -0.06
    ĥn
    -0.06
    ylon
    -0.06
    nech
    -0.06
    POSITIVE LOGITS
     hã
    0.06
    æ³ī
    0.06
    ÌĢ
    0.06
    ipel
    0.06
    semblies
    0.06
    HWND
    0.06
    ungan
    0.06
    oger
    0.06
    ACH
    0.06
    phanumeric
    0.06
    Activations Density 0.011%

    No Known Activations