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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 84636
    Prev
    Next
    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “cell” (and its plural “cells”) in biological contexts.

    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
    features
    -0.06
    _BUILD
    -0.06
    -with
    -0.06
    OLDER
    -0.06
     components
    -0.06
    _js
    -0.06
    аров
    -0.06
     nackte
    -0.06
    ___
    -0.06
    swith
    -0.06
    POSITIVE LOGITS
    UCT
    0.08
    ลง
    0.07
     �
    0.07
     canv
    0.06
    methodName
    0.06
     Punch
    0.06
     fungi
    0.06
    евой
    0.06
     bust
    0.06
     Steelers
    0.06
    Activations Density 0.009%

    No Known Activations