© 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. 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. 57965
    Prev
    Next
    INDEX
    Explanations

    general language

    np_max-act · gemini-2.0-flash

    The neuron activates on positive evaluative words—especially adjectives and intensifiers that praise qualities or performance.

    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
    YP
    -0.07
    _detection
    -0.07
    omas
    -0.06
     assessments
    -0.06
    OPY
    -0.06
     Beled
    -0.06
     graveyard
    -0.06
    -view
    -0.06
    iness
    -0.06
     Opr
    -0.06
    POSITIVE LOGITS
     сфер
    0.07
     t
    0.07
     schö
    0.07
     alanı
    0.06
     multip
    0.06
    っち
    0.06
    เตร
    0.06
     절
    0.06
     SZ
    0.06
     techn
    0.06
    Activations Density 0.036%

    No Known Activations