© 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. 2346
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ÑĢап
    -0.07
    hm
    -0.06
     Bey
    -0.06
     detail
    -0.06
     –
    -0.06
    -spinner
    -0.06
    RAP
    -0.06
     accuracy
    -0.06
     reality
    -0.06
     rated
    -0.05
    POSITIVE LOGITS
     Nack
    0.08
     nack
    0.07
    angan
    0.07
    InThe
    0.07
    TURE
    0.07
    anim
    0.07
     ((__
    0.07
    nÃŃk
    0.07
    ToFit
    0.07
    ettes
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.