© 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. 6887
    Prev
    Next
    INDEX
    Explanations

    programming commands

    np_max-act · gemini-2.0-flash

    This neuron detects common API operation verbs (e.g. Create, Delete, Get, Describe, Start, Stop) in documentation or code.

    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
     acrylic
    -0.06
    _policy
    -0.06
    phas
    -0.06
     Gast
    -0.06
    XObject
    -0.06
    ality
    -0.06
    	count
    -0.06
    Parameters
    -0.06
    .pix
    -0.06
    count
    -0.06
    POSITIVE LOGITS
    ?><?
    0.07
     Michele
    0.07
    _pr
    0.07
     paced
    0.06
    strukce
    0.06
    eştir
    0.06
    miştir
    0.06
     Sgt
    0.06
    .XRLabel
    0.06
     سپتامبر
    0.06
    Activations Density 0.042%

    No Known Activations