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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56946
    Prev
    Next
    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash

    This neuron detects the numeric markers (e.g. “2,” “3,” “4,” etc.) that denote steps in a numbered list of instructions.

    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
     sexual
    -0.07
     vie
    -0.06
     Buch
    -0.06
     righteous
    -0.06
     reduces
    -0.06
     frec
    -0.06
     sentinel
    -0.06
     founding
    -0.06
     On
    -0.06
     Ал
    -0.06
    POSITIVE LOGITS
    183
    0.08
    ینه
    0.07
    ???↵↵
    0.07
    ('-',
    0.07
    233
    0.07
     '-';↵
    0.07
    Meteor
    0.07
     AVG
    0.06
    拥
    0.06
    QE
    0.06
    Activations Density 0.040%

    No Known Activations