© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57156
    Prev
    Next
    INDEX
    Explanations

    confess

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “confession” (and its variants like “confessing”), i.e. on prompts asking to write a confession.

    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
     Artem
    -0.07
     Re
    -0.07
     Erick
    -0.07
    .Dark
    -0.07
     Aster
    -0.07
     Walmart
    -0.07
    Tim
    -0.07
    Jul
    -0.07
    .sqrt
    -0.07
     Evel
    -0.07
    POSITIVE LOGITS
     confessed
    0.11
     confess
    0.11
     confession
    0.10
    IFEST
    0.07
     thừa
    0.07
     коміс
    0.07
    备份
    0.06
    OPSIS
    0.06
    lices
    0.06
    {{--
    0.06
    Activations Density 0.003%

    No Known Activations