© 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
    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. 124903
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash

    The neuron fires on dot-prefixed identifiers (e.g. “.console”, “.log”, “.max_line”, 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
     gets
    -0.07
    (".")
    -0.07
    .sheet
    -0.07
    cona
    -0.06
     messed
    -0.06
     lazy
    -0.06
     carro
    -0.06
    -server
    -0.06
     Molecular
    -0.06
     mohlo
    -0.06
    POSITIVE LOGITS
      ↵↵
    0.06
    ンパ
    0.06
    �
    0.06
     limb
    0.06
    _be
    0.06
     PROGMEM
    0.06
    ائی
    0.06
     revised
    0.06
     grupo
    0.06
     электри
    0.06
    Activations Density 0.070%

    No Known Activations