© 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. 81334
    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
     [âĢ¦]
    -0.07
    iez
    -0.07
     stereotypes
    -0.06
    keyCode
    -0.06
     [âĢ¦
    -0.06
    âĢİ
    -0.06
    ï
    -0.06
    adero
    -0.06
    ă
    -0.06
     snapchat
    -0.06
    POSITIVE LOGITS
     Erect
    0.08
     Pub
    0.07
    .tex
    0.07
    ãĥ¼ãĥĬ
    0.06
    isin
    0.06
     Sax
    0.06
    èĭ
    0.06
    ï¿
    0.06
    abaj
    0.06
    acha
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.