© 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. 72363
    Prev
    Next
    INDEX
    Explanations

    references to the name "Rohan" and its variations

    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
    957
    -0.07
    918
    -0.07
    umas
    -0.06
    idores
    -0.06
    orns
    -0.06
    837
    -0.06
    ÏĮÏģ
    -0.06
     Void
    -0.06
    uality
    -0.06
    744
    -0.06
    POSITIVE LOGITS
    efeller
    0.08
    iginal
    0.07
     ro
    0.07
    Ro
    0.07
    (ro
    0.07
    enda
    0.07
     Ro
    0.06
    Âłro
    0.06
    avirus
    0.06
    oco
    0.06
    Activations Density 0.032%

    No Known Activations