© 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. 7827
    Prev
    Next
    INDEX
    Explanations

    friend

    np_max-act · gemini-2.0-flash

    biographical details about authors and their literary contributions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words and contexts signaling friendships or friendly relationships.

    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
     merit
    -0.06
    _duplicates
    -0.06
    다가
    -0.06
    っている
    -0.06
    、私
    -0.06
     curt
    -0.05
    投资
    -0.05
    πως
    -0.05
     dans
    -0.05
    .previous
    -0.05
    POSITIVE LOGITS
     ><?
    0.07
    !
    0.07
    (['/
    0.06
    541
    0.06
     explan
    0.06
     submar
    0.06
    .th
    0.06
     ##↵
    0.06
    ={$
    0.06
     спіл
    0.06
    Activations Density 0.031%

    No Known Activations