© 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. 117043
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reference or citation

    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
     slip
    -0.07
    hu
    -0.06
     assort
    -0.06
     Slip
    -0.06
     sm
    -0.06
    ser
    -0.06
    :
    -0.06
     bree
    -0.06
     ser
    -0.06
     maj
    -0.05
    POSITIVE LOGITS
     latter
    0.09
    oji
    0.08
     DropIndex
    0.08
    entai
    0.08
    incerely
    0.08
    semblies
    0.08
    óng
    0.08
    phalt
    0.07
    reshold
    0.07
    neau
    0.07
    Activations Density 0.074%

    No Known Activations