© 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. 68795
    Prev
    Next
    INDEX
    Explanations

    ac

    np_max-act · gemini-2.0-flash

    Neuron 4 detects the word “peacetime.”

    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
    wife
    -0.08
     Wife
    -0.07
     данны
    -0.07
    ูต
    -0.07
     transit
    -0.06
     Wig
    -0.06
     granny
    -0.06
     �
    -0.06
    성이
    -0.06
    님
    -0.06
    POSITIVE LOGITS
    _journal
    0.07
     Applying
    0.07
    (selector
    0.06
    alan
    0.06
    ");}↵
    0.06
    Contrib
    0.06
     عدد
    0.06
    >');
↵
    0.06
    ‐‐
    0.06
     adapting
    0.06
    Activations Density 0.255%

    No Known Activations