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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130550
    Prev
    Next
    INDEX
    Explanations

    extend

    np_max-act · gemini-2.0-flash

    The neuron fires on discourse cues that indicate extending prior work (e.g. “extend,” “extends,” “extended”).

    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
     dl
    -0.07
    redient
    -0.07
         
    -0.06
     BT
    -0.06
     chk
    -0.06
    )((((
    -0.06
          
    -0.06
    .Option
    -0.06
    .utility
    -0.06
     bye
    -0.06
    POSITIVE LOGITS
     acompanh
    0.07
    SAN
    0.07
     yapılan
    0.07
    ativní
    0.06
    	align
    0.06
     Philippine
    0.06
    チャ
    0.06
    Sy
    0.06
    SQLException
    0.06
     일어
    0.06
    Activations Density 0.026%

    No Known Activations