© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6312
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron never activates (all zero), so it doesn’t detect any specific pattern.

    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
    Chip
    -0.06
     gam
    -0.06
     mai
    -0.06
    ặp
    -0.06
    _UI
    -0.06
    antor
    -0.06
    (크기
    -0.06
     displaying
    -0.06
    }()↵
    -0.05
    persistent
    -0.05
    POSITIVE LOGITS
     Rough
    0.07
     ngôn
    0.07
    906
    0.07
     cons
    0.06
     aggress
    0.06
     veget
    0.06
    χρι
    0.06
     pomoci
    0.06
     obsessive
    0.06
     acompañ
    0.06
    Activations Density 0.051%

    No Known Activations