© 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. 91583
    Prev
    Next
    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash

    The neuron is essentially “dead” in these examples—it never activates on any token, so it isn’t detecting any pattern.

    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
    (permission
    -0.07
     Jon
    -0.07
    Jon
    -0.07
    Rocket
    -0.07
     Hakk
    -0.07
    Collector
    -0.07
     hayır
    -0.07
    333
    -0.07
     produkt
    -0.07
    ahir
    -0.06
    POSITIVE LOGITS
     Sarah
    0.08
     Moodle
    0.07
     sitting
    0.07
     stew
    0.07
     desk
    0.07
     Cristina
    0.07
     لل
    0.07
    Sarah
    0.06
     intoler
    0.06
     stressful
    0.06
    Activations Density 0.006%

    No Known Activations