Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109550
    Prev
    Next
    INDEX
    Explanations

    takes

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is pick up numeric literal tokens (especially floating-point numbers) in code.

    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
     하면
    -0.08
     Chap
    -0.07
     Comm
    -0.07
     Sof
    -0.07
    Hat
    -0.06
    ु�
    -0.06
    นส
    -0.06
    }$/
    -0.06
     EEPROM
    -0.06
     rang
    -0.06
    POSITIVE LOGITS
     erkek
    0.07
    :[],↵
    0.06
    〜
    0.06
     kidnapped
    0.06
    -cart
    0.06
    ehir
    0.06
     Symposium
    0.06
    ік
    0.06
    tul
    0.06
    anoi
    0.06
    Activations Density 0.016%

    No Known Activations