© 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. 2109
    Prev
    Next
    INDEX
    Explanations

    request-related phrases and terms

    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
     Tay
    -0.06
    ynch
    -0.06
    isu
    -0.06
    åı°
    -0.06
    cratch
    -0.06
    stry
    -0.05
    romise
    -0.05
    igh
    -0.05
    jian
    -0.05
    bower
    -0.05
    POSITIVE LOGITS
    rary
    0.08
    lep
    0.07
    evi
    0.07
    деÑĢ
    0.07
    unde
    0.06
     bureauc
    0.06
    Ïĥια
    0.06
    .Padding
    0.06
    ORB
    0.06
    ulse
    0.06
    Activations Density 0.000%

    No Known Activations