© 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. 81400
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to age and status

    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
    uet
    -0.08
    alım
    -0.07
    à¸Ħร
    -0.07
    ivre
    -0.07
    chalk
    -0.07
    uent
    -0.07
    ieves
    -0.07
     Equals
    -0.06
    umlu
    -0.06
    éĻ·
    -0.06
    POSITIVE LOGITS
     folk
    0.08
     ones
    0.07
     people
    0.07
     cannot
    0.07
     might
    0.07
    folk
    0.07
     saying
    0.06
     must
    0.06
     really
    0.06
     personnel
    0.06
    Activations Density 0.072%

    No Known Activations