© 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. 41194
    Prev
    Next
    INDEX
    Explanations

    Financial market reports

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens (particularly financial figures and percentages) in the text.

    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
     Nutrition
    -0.07
    /doc
    -0.07
    /oct
    -0.07
    iom
    -0.06
     Republican
    -0.06
    hed
    -0.06
    OT
    -0.06
    	AT
    -0.06
    .linear
    -0.06
    	ep
    -0.06
    POSITIVE LOGITS
     é
    0.07
    обыти
    0.07
     eşit
    0.06
     hedef
    0.06
     vyd
    0.06
    ancements
    0.06
     Certain
    0.06
     viagra
    0.06
    ับความ
    0.06
     szy
    0.06
    Activations Density 0.008%

    No Known Activations