© 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. 27765
    Prev
    Next
    INDEX
    Explanations

    instances of events and exhibitions

    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
    ìĦł
    -0.06
    elson
    -0.06
     Lair
    -0.06
     bore
    -0.05
     undert
    -0.05
    otte
    -0.05
     Pet
    -0.05
    ç´Ģ
    -0.05
    fur
    -0.05
     Hoy
    -0.05
    POSITIVE LOGITS
    achs
    0.08
     will
    0.08
    #ae
    0.07
     Tiếng
    0.07
    -BEGIN
    0.07
     discrepan
    0.07
     sẽ
    0.07
    Ùģت
    0.07
    .tencent
    0.07
    meyi
    0.07
    Activations Density 0.018%

    No Known Activations