© 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. 89259
    Prev
    Next
    INDEX
    Explanations

    Contentious topics

    np_max-act · gemini-2.0-flash

    issues related to political discourse and governance.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the evaluative terms “right” and especially “wrong.”

    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
     filmmaker
    -0.07
     개
    -0.07
    primir
    -0.07
    に出
    -0.06
    gray
    -0.06
    getline
    -0.06
    model
    -0.06
    liğine
    -0.06
    ΙΟΥ
    -0.06
     ctrl
    -0.05
    POSITIVE LOGITS
     ajud
    0.07
    .temperature
    0.07
     fık
    0.07
    _VC
    0.07
     мет
    0.07
    PR
    0.06
     مذ
    0.06
     )(
    0.06
    )dealloc
    0.06
    (MAX
    0.06
    Activations Density 0.048%

    No Known Activations