© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 113368
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    This neuron detects first-person travel plans or trip-related statements (phrases like "I'm going on a trip," "I'm staying in ...," or "traveling to ...").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ゞ
    -0.07
     â
    -0.07
    extract
    -0.07
     montage
    -0.06
     Ancient
    -0.06
    ेप
    -0.06
    (@"
    -0.06
    前
    -0.06
     Nov
    -0.06
    [thread
    -0.06
    POSITIVE LOGITS
    .Asset
    0.07
     ENG
    0.06
     существует
    0.06
    eroon
    0.06
     MARK
    0.06
    181
    0.06
    орі
    0.06
    σταν
    0.06
    	onClick
    0.06
     двиг
    0.06
    Activations Density 0.087%

    No Known Activations