© 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
    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. 110387
    Prev
    Next
    INDEX
    Explanations

    Stat increases

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are part of the assistant’s generated response text (i.e. model‐output tokens rather than user input).

    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
    .integration
    -0.07
    .department
    -0.07
     charitable
    -0.06
     green
    -0.06
     buys
    -0.06
    Authenticated
    -0.06
    plements
    -0.06
    odzi
    -0.06
    utowired
    -0.06
     decimal
    -0.06
    POSITIVE LOGITS
     fizik
    0.07
    іно
    0.07
     kredi
    0.06
    ,sizeof
    0.06
     greatly
    0.06
    	Q
    0.06
     AttributeSet
    0.06
    ourage
    0.06
    ))/
    0.06
    emotion
    0.06
    Activations Density 0.010%

    No Known Activations