© 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. 12217
    Prev
    Next
    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash

    The neuron activates on role‐or‐title phrases in “who is/was the [title] of/at/in [entity]” questions.

    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
     UIStoryboard
    -0.06
    晶
    -0.06
    grades
    -0.06
    lane
    -0.06
    .steps
    -0.06
    -saving
    -0.05
    Naz
    -0.05
     Expires
    -0.05
    iffe
    -0.05
    UNDLE
    -0.05
    POSITIVE LOGITS
    BUTTONDOWN
    0.07
     sahibi
    0.07
    Direct
    0.07
    /*.
    0.06
     aim
    0.06
     IDirect
    0.06
    tiv
    0.06
    acağız
    0.06
    WARD
    0.06
     Gson
    0.06
    Activations Density 0.090%

    No Known Activations