© 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. 4610
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives that convey resistance or avoidance

    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
    imenti
    -0.07
    Å¡il
    -0.07
    äll
    -0.06
    porte
    -0.06
    opher
    -0.06
    atori
    -0.06
    ipheral
    -0.06
    aga
    -0.06
    dispose
    -0.06
    ige
    -0.06
    POSITIVE LOGITS
     away
    0.09
    éĥ
    0.07
     Pul
    0.07
    ISCO
    0.07
     responsibilities
    0.07
    olson
    0.07
    isco
    0.06
    #+
    0.06
     discomfort
    0.06
     Wander
    0.06
    Activations Density 0.003%

    No Known Activations