© 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. 80460
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recommendations or suggestions about places or experiences

    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
    owi
    -0.08
    yme
    -0.07
    zew
    -0.07
    .epam
    -0.07
    odzi
    -0.07
    á»·
    -0.07
    Wunused
    -0.07
    먹
    -0.07
    µľ
    -0.07
    ALSE
    -0.07
    POSITIVE LOGITS
     ticket
    0.07
     missing
    0.07
    0.06
     right
    0.06
     spot
    0.06
     Cole
    0.05
     hookup
    0.05
    ends
    0.05
    1
    0.05
     Super
    0.05
    Activations Density 0.015%

    No Known Activations