Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12872
    Prev
    Next
    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash

    The neuron specifically detects French callback request phrasing (e.g. “rappeler,” “appeler,” and related personal pronouns around a phone-back ask).

    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
     Hide
    -0.07
    zman
    -0.07
    نج
    -0.06
     That
    -0.06
    .flat
    -0.06
    .Mouse
    -0.06
     Bud
    -0.06
     Neville
    -0.06
     One
    -0.06
    ruk
    -0.06
    POSITIVE LOGITS
    .Dense
    0.06
    FromNib
    0.06
    ViewHolder
    0.06
    POSITION
    0.06
    Study
    0.06
    issippi
    0.06
     YT
    0.06
    YLES
    0.06
     χώ
    0.06
     cứu
    0.06
    Activations Density 0.011%

    No Known Activations