© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125057
    Prev
    Next
    INDEX
    Explanations

    Coherent English text

    np_max-act · gemini-2.0-flash

    This neuron detects instructional/advice language, especially the second-person pronoun “you” and related modal verbs in how-to or guidance sentences.

    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
    ENCED
    -0.07
     obtaining
    -0.07
     d
    -0.07
     inadvertently
    -0.06
     đáo
    -0.06
    Meeting
    -0.06
     utiliser
    -0.06
     buried
    -0.06
     براي
    -0.06
     omitted
    -0.06
    POSITIVE LOGITS
    .MONTH
    0.06
    cop
    0.06
    _THEME
    0.06
    (rx
    0.06
    مام
    0.06
    「そう
    0.06
    JM
    0.06
     是否
    0.06
    �
    0.06
    =head
    0.06
    Activations Density 0.040%

    No Known Activations