© 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. 109175
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    This neuron detects Lisp‐style PDDL planning problem definitions, i.e. parenthesized “(define …)” blocks describing objects, init, and goal.

    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
    Cad
    -0.07
    _UC
    -0.06
    解决
    -0.06
    界
    -0.06
     exp
    -0.06
    Engine
    -0.06
     ASC
    -0.06
     apple
    -0.06
     "=
    -0.06
     beats
    -0.06
    POSITIVE LOGITS
    (datos
    0.07
     Futures
    0.07
    namen
    0.07
    (best
    0.07
     these
    0.07
    (thing
    0.06
     Stra
    0.06
     EVENTS
    0.06
    undef
    0.06
    ariant
    0.06
    Activations Density 0.043%

    No Known Activations