© 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. 7342
    Prev
    Next
    INDEX
    Explanations

    35

    np_max-act · gemini-2.0-flash

    legal terminology and references to court rules related to sentencing and appeals.

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

    The neuron detects occurrences of the number “35” when it appears as part of a legal rule citation (e.g. “Rule 35”).

    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
    QUOTE
    -0.07
     解
    -0.07
     Left
    -0.07
    Got
    -0.06
    Û
    -0.06
    foreach
    -0.06
    "Do
    -0.06
     помощ
    -0.06
    "You
    -0.06
     survive
    -0.06
    POSITIVE LOGITS
     безопасности
    0.07
     �
    0.07
     существ
    0.07
     MIME
    0.06
     �
    0.06
     ули
    0.06
     breathing
    0.06
    _NODE
    0.06
    AccessType
    0.06
     Anadolu
    0.06
    Activations Density 0.001%

    No Known Activations