Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26936
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/discussions

    np_max-act · gemini-2.0-flash

    This neuron selectively fires on uppercase technical abbreviations or acronyms.

    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
     Medium
    -0.07
    acağım
    -0.07
    ibraltar
    -0.06
     FRONT
    -0.06
     hailed
    -0.06
    iti
    -0.06
    _index
    -0.06
     서비스
    -0.06
    /octet
    -0.06
     Пари
    -0.06
    POSITIVE LOGITS
    /message
    0.07
     οικο
    0.07
     tender
    0.06
     denominator
    0.06
     informatie
    0.06
    ynamics
    0.06
     ออนไลน
    0.06
    clave
    0.06
    mur
    0.06
     coronary
    0.06
    Activations Density 0.107%

    No Known Activations