© 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. 55167
    Prev
    Next
    INDEX
    Explanations

    information related to class registration and costs

    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
    loth
    -0.07
    loser
    -0.05
    stav
    -0.05
     Glas
    -0.05
     inter
    -0.05
    uraa
    -0.05
    arn
    -0.05
     citizenship
    -0.05
    estination
    -0.05
     ([]
    -0.05
    POSITIVE LOGITS
     course
    0.08
    Course
    0.07
     participant
    0.07
     Participant
    0.06
    /course
    0.06
     emailing
    0.06
    course
    0.06
    PRI
    0.06
    fers
    0.06
    chia
    0.06
    Activations Density 0.014%

    No Known Activations