© 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. 42702
    Prev
    Next
    INDEX
    Explanations

    ch

    np_max-act · gemini-2.0-flash

    The neuron fires on isolated punctuation or operator symbols in code (e.g. single-character tokens like “.”, “\”, “#”, 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
    альных
    -0.07
    ;
    ↵
    ↵
    ↵
    -0.07
     debates
    -0.07
     indicators
    -0.06
     goog
    -0.06
    		
    ↵
    -0.06
    Introduced
    -0.06
     обс
    -0.06
    iques
    -0.06
    워크
    -0.06
    POSITIVE LOGITS
     包
    0.06
    CharCode
    0.06
     Αλ
    0.06
     '.$
    0.06
     mimetype
    0.06
     strang
    0.06
     �
    0.06
     encountering
    0.06
    (embed
    0.06
     nl
    0.06
    Activations Density 0.005%

    No Known Activations