© 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. 13009
    Prev
    Next
    INDEX
    Explanations

    online dating services

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of essays and related academic writing terms (e.g. “essay,” “persuasive,” “writing,” “students,” “grade”).

    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
    .demo
    -0.07
    brief
    -0.07
    .Sp
    -0.06
     multiline
    -0.06
    [Test
    -0.06
    -pass
    -0.06
    ara
    -0.06
     Departments
    -0.06
    detalle
    -0.06
    _substr
    -0.06
    POSITIVE LOGITS
     contentious
    0.06
    .'↵↵
    0.06
    RecognitionException
    0.06
    lob
    0.06
     giáo
    0.06
     GPI
    0.06
     можуть
    0.06
     लगभग
    0.06
     Grip
    0.06
     kriz
    0.06
    Activations Density 0.011%

    No Known Activations