© 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. 128739
    Prev
    Next
    INDEX
    Explanations

    follow

    np_max-act · gemini-2.0-flash

    The neuron detects call-to-action prompts encouraging reader engagement (e.g. follow, subscribe, click-here) on social media or related platforms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    narratives related to culinary events and experiences.

    oai_token-act-pair · gpt-4o-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
    ンツ
    -0.07
    dice
    -0.06
    uestos
    -0.06
    část
    -0.06
    ния
    -0.06
    annotations
    -0.06
    eddar
    -0.06
     Scotland
    -0.06
    hooks
    -0.06
     beden
    -0.06
    POSITIVE LOGITS
     DEN
    0.07
    Intern
    0.07
    hythm
    0.07
    اا
    0.06
     Mist
    0.06
    ，更
    0.06
    CurrentValue
    0.06
    _media
    0.06
     olmadığını
    0.06
     AV
    0.06
    Activations Density 0.010%

    No Known Activations