© 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. 5543
    Prev
    Next
    INDEX
    Explanations

    references to user account management and instructions related to online services

    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
    iss
    -0.07
    ugh
    -0.07
    /cgi
    -0.06
    wm
    -0.06
     éĻ
    -0.06
     term
    -0.06
     se
    -0.06
     tr
    -0.06
     anim
    -0.06
    oleon
    -0.05
    POSITIVE LOGITS
     Hlav
    0.08
    ersist
    0.08
    ToObject
    0.08
    aho
    0.07
    .Assertions
    0.07
    kate
    0.07
     bottom
    0.07
    dech
    0.07
    avig
    0.07
    егоÑĢ
    0.07
    Activations Density 0.022%

    No Known Activations