© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 94298
    Prev
    Next
    INDEX
    Explanations

    end tags in HTML or XML code

    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
    ively
    -0.07
    yr
    -0.07
    oland
    -0.07
    erson
    -0.07
    y
    -0.06
    antt
    -0.06
    ivia
    -0.06
    کر
    -0.06
    psz
    -0.06
    son
    -0.06
    POSITIVE LOGITS
    Ấ
    0.07
    Ø©
    0.07
     RAT
    0.07
     ÑĤиж
    0.07
    edBy
    0.06
    ÙĦ
    0.06
    IService
    0.06
    onyms
    0.06
    hone
    0.06
    ocks
    0.06
    Activations Density 0.023%

    No Known Activations