© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12656
    Prev
    Next
    INDEX
    Explanations

    @gmail

    np_max-act · gemini-2.0-flash

    This neuron activates on email address patterns (e.g., “<name>@<domain>”).

    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
    494
    -0.07
     document
    -0.07
     corridors
    -0.07
    ep
    -0.06
    _crit
    -0.06
    .equ
    -0.06
     seab
    -0.06
     rever
    -0.06
    Helvetica
    -0.06
     watch
    -0.06
    POSITIVE LOGITS
    @gmail
    0.12
     الغ
    0.07
    (img
    0.07
    мир
    0.07
    lad
    0.07
     Jimmy
    0.06
     deviceId
    0.06
     แก
    0.06
    肯
    0.06
    ن
    0.06
    Activations Density 0.002%

    No Known Activations