© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57213
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs

    np_max-act · gemini-2.0-flash

    This neuron responds to longer, multi-syllable content words (especially adjectives and adverbs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    respect
    -0.06
    Hundreds
    -0.06
    SSI
    -0.06
    敷
    -0.06
     Assigned
    -0.06
     глуб
    -0.06
     either
    -0.06
    amilies
    -0.06
     adversaries
    -0.06
    IH
    -0.06
    POSITIVE LOGITS
    }{↵
    0.07
    )__
    0.06
     fragmentManager
    0.06
    :"+
    0.06
     */,
    0.06
    ")+
    0.06
    ];//
    0.06
     addTo
    0.06
    }
↵
↵
↵
↵
    0.06
     astrology
    0.06
    Activations Density 0.052%

    No Known Activations