© 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. 2041
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate some level of criticism or negativity towards people or things

    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
    ptal
    -0.07
    aton
    -0.06
    ilon
    -0.06
    ets
    -0.06
    ady
    -0.06
     UITapGestureRecognizer
    -0.06
    ações
    -0.06
    atedRoute
    -0.06
    yn
    -0.06
    661
    -0.06
    POSITIVE LOGITS
     thing
    0.08
     things
    0.07
     people
    0.07
     stuff
    0.07
    swer
    0.07
    robat
    0.06
    stitial
    0.06
    à¹ĭ
    0.06
    thing
    0.06
    tero
    0.06
    Activations Density 0.028%

    No Known Activations