© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55603
    Prev
    Next
    INDEX
    Explanations

    research surveys

    np_max-act · gemini-2.0-flash

    The neuron flags words and phrases describing study methods or procedures (e.g. “survey,” “conducted,” “carried out,” “using”).

    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
     HOUSE
    -0.07
     whales
    -0.07
     el
    -0.07
     rivers
    -0.06
    deep
    -0.06
    etype
    -0.06
    alan
    -0.06
    orgot
    -0.06
    еш
    -0.06
     memes
    -0.06
    POSITIVE LOGITS
     opportun
    0.07
    \widgets
    0.06
    信用
    0.06
     NullPointerException
    0.06
     --------------------
    0.06
     containerView
    0.06
    _UnityEngine
    0.06
    .createSequentialGroup
    0.06
    드는
    0.06
     болезни
    0.06
    Activations Density 0.029%

    No Known Activations