© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53875
    Prev
    Next
    INDEX
    Explanations

    the character "Ranbir" and its variations in a narrative context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    yat
    -0.07
    944
    -0.07
    iomanip
    -0.07
    eyle
    -0.07
    chalk
    -0.07
     Majority
    -0.07
    Compat
    -0.07
    ussy
    -0.07
    ↵↵
    -0.07
    aft
    -0.07
    POSITIVE LOGITS
    vier
    0.07
    agrams
    0.07
    atal
    0.07
    asing
    0.07
     pl
    0.07
     ob
    0.07
    ieri
    0.06
    ake
    0.06
    bot
    0.06
    496
    0.06
    Activations Density 0.005%

    No Known Activations