© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 126720
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron fires on specialized technical or patent-style content words and descriptors (e.g. “powered,” “compartment,” “conduit,” “connected”) characteristic of engineering/specification language.

    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
    \htdocs
    -0.08
     Ao
    -0.06
     Nashville
    -0.06
    material
    -0.06
    führ
    -0.05
    еку
    -0.05
    ~~
    -0.05
    	Register
    -0.05
     envision
    -0.05
    erea
    -0.05
    POSITIVE LOGITS
    ählt
    0.07
    itung
    0.07
     Silent
    0.07
    يلم
    0.07
    iqueta
    0.07
    __(
    0.06
     MARK
    0.06
     двух
    0.06
     พร
    0.06
    uetype
    0.06
    Activations Density 0.109%

    No Known Activations