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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6012
    Prev
    Next
    INDEX
    Explanations

    instructions or requirements

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases that express necessity or sufficiency (e.g. “need,” “must,” “suffices,” “have to,” “only to”).

    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
     Exec
    -0.07
     negotiate
    -0.07
     Generate
    -0.07
    lük
    -0.06
    zo
    -0.06
    ,no
    -0.06
     Radio
    -0.06
     Lance
    -0.06
     tuyên
    -0.06
     Plasma
    -0.06
    POSITIVE LOGITS
    [w
    0.07
    (theta
    0.07
    _problem
    0.06
    위를
    0.06
    ивания
    0.06
    ;}
    ↵
    0.06
     العربية
    0.06
    ==========
    0.06
    .CONFIG
    0.06
    Off
    0.06
    Activations Density 0.019%

    No Known Activations