© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6352
    Prev
    Next
    INDEX
    Explanations

    dynamics

    np_max-act · gemini-2.0-flash

    This neuron detects specialized dynamical‐systems and nonlinear‐physics terminology—words like “chaotic,” “periodic,” “orbits,” “phase transitions,” “maps,” etc.

    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
    subst
    -0.07
     Chevron
    -0.06
     часу
    -0.06
    oftware
    -0.06
     evapor
    -0.06
    >}</
    -0.06
    urd
    -0.06
    א
    -0.06
    isle
    -0.06
     ชนะ
    -0.06
    POSITIVE LOGITS
     Operations
    0.06
     occupations
    0.06
     intention
    0.06
    _ENTER
    0.06
    TypeInfo
    0.06
     év
    0.06
    _personal
    0.06
     ApplicationUser
    0.06
    稍
    0.06
    minimal
    0.06
    Activations Density 0.011%

    No Known Activations