© 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
    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. 91513
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point number tokens (decimal values used for layout/indentation or formatting).

    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
    Scar
    -0.07
     Peach
    -0.06
    /pg
    -0.06
    .Mod
    -0.06
     роз
    -0.06
    �
    -0.06
    Yu
    -0.06
     smashed
    -0.06
    erver
    -0.06
     VS
    -0.06
    POSITIVE LOGITS
      
    0.07
     تهیه
    0.06
     voi
    0.06
     incentiv
    0.06
    468
    0.06
     cin
    0.06
     Сан
    0.06
    ent
    0.06
    (sheet
    0.06
     ingres
    0.06
    Activations Density 0.005%

    No Known Activations