© 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. 11-RESID-POST-AA
    6. 89729
    Prev
    Next
    INDEX
    Explanations

    Roman

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “Roman.”

    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
    8
    -0.07
    Half
    -0.07
    咲
    -0.07
     Slayer
    -0.07
    Aug
    -0.06
     Guil
    -0.06
    Decrypt
    -0.06
     Ud
    -0.06
    ','-
    -0.06
    出口
    -0.06
    POSITIVE LOGITS
     Roman
    0.13
    Roman
    0.11
     roman
    0.09
    roman
    0.09
    man
    0.08
    าน
    0.08
     Confederate
    0.08
    MAS
    0.08
     column
    0.08
    ωνα
    0.07
    Activations Density 0.004%

    No Known Activations