© 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. 95373
    Prev
    Next
    INDEX
    Explanations

    signs of correspondence or communication within the text

    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
    ardon
    -0.07
    lijke
    -0.07
    ãĥ¼ãĥį
    -0.06
     RaisePropertyChanged
    -0.06
    athan
    -0.06
    cod
    -0.06
    olar
    -0.06
    insky
    -0.06
    å«Į
    -0.06
     cups
    -0.06
    POSITIVE LOGITS
     Column
    0.08
    Ñıк
    0.07
     column
    0.07
     Columns
    0.07
    iban
    0.07
     columnist
    0.07
    -column
    0.07
     letter
    0.06
     COLUMN
    0.06
     Editorial
    0.06
    Activations Density 0.014%

    No Known Activations