© 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. 44152
    Prev
    Next
    INDEX
    Explanations

    "In addition to" phrase

    np_max-act · gemini-2.0-flash

    The neuron fires on non-specific, generalizing adjectives and nouns (e.g. “various,” “functional,” “purposes”) indicating broad or miscellaneous functions.

    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
    past
    -0.06
     Rights
    -0.06
    -table
    -0.06
    .rf
    -0.06
    라이
    -0.06
     Parallel
    -0.06
    周期
    -0.06
     αρ
    -0.06
     strtotime
    -0.06
    ежать
    -0.06
    POSITIVE LOGITS
    ';↵↵↵
    0.06
     点
    0.06
     Berg
    0.06
     functionality
    0.06
    isi
    0.06
    .scala
    0.06
    	↵	↵	↵
    0.06
    +x
    0.06
    \helpers
    0.06
    няття
    0.06
    Activations Density 0.038%

    No Known Activations