Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43582
    Prev
    Next
    INDEX
    Explanations

    autofocus

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric specification details—measurements, counts, and values (e.g. “45-point,” “3 fps,” “24 mm,” “1.399”), especially in camera spec lists.

    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
    -that
    -0.07
    .times
    -0.07
     Tent
    -0.07
     Cr
    -0.07
    kategori
    -0.07
     champagne
    -0.06
     piano
    -0.06
    (Char
    -0.06
     preacher
    -0.06
     bells
    -0.06
    POSITIVE LOGITS
    Dealer
    0.07
    ++]
    0.06
    arging
    0.06
     clinic
    0.06
    anki
    0.05
     Http
    0.05
    ('</
    0.05
     ironically
    0.05
    ATHER
    0.05
    ĩ
    0.05
    Activations Density 0.005%

    No Known Activations