© 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. 15-RESID-POST-AA
    11. 85760
    Prev
    Next
    INDEX
    Explanations

    process of changing

    np_max-act · gemini-2.0-flash

    Phrases that describe the order or direction of processing (especially working backwards or starting from the middle / reverse or middle-out traversal).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ňují
    -0.08
    IL
    -0.07
    ِّ
    -0.07
     _)
    -0.06
    .Chain
    -0.06
    'il
    -0.06
    .ds
    -0.06
     leurs
    -0.06
     annoyed
    -0.06
     unlikely
    -0.06
    POSITIVE LOGITS
    ).'</
    0.07
    栏
    0.06
     Macro
    0.06
    .vm
    0.06
    measurement
    0.06
     withdrawals
    0.06
     sugars
    0.06
    Bright
    0.06
    平方公里
    0.06
     Intelligent
    0.06
    Activations Density 0.021%

    No Known Activations