© 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. 7-RESID-POST-AA
    11. 42827
    Prev
    Next
    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash

    It detects headings that introduce case or docket numbers/citations (the "No."/case-number lines in legal document headers).

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     řekl
    -0.07
     adicion
    -0.06
    LOSS
    -0.06
    zp
    -0.06
     BL
    -0.06
     XX
    -0.06
    ��
    -0.06
     сл
    -0.06
     příprav
    -0.06
    екотор
    -0.06
    POSITIVE LOGITS
    ンダ
    0.06
    ClickListener
    0.06
    .dispose
    0.06
    Validation
    0.06
    /thumb
    0.06
    traction
    0.06
    ?>">↵
    0.06
     {}
↵
    0.06
     tracked
    0.06
    ordes
    0.06
    Activations Density 0.010%

    No Known Activations