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. 15-RESID-POST-AA
    6. 91276
    Prev
    Next
    INDEX
    Explanations

    web content

    np_max-act · gemini-2.0-flash

    sentences or phrases that give instructions, how-to steps, or action-oriented guidance.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    易
    -0.06
     glove
    -0.06
    imate
    -0.06
    _der
    -0.06
    istrate
    -0.06
    															
    -0.06
     discreet
    -0.06
    μιουργ
    -0.06
     chants
    -0.06
    																	
    -0.06
    POSITIVE LOGITS
    _success
    0.07
     BOOK
    0.07
    町
    0.07
     okay
    0.07
    _limit
    0.07
     один
    0.06
    /s
    0.06
    فع
    0.06
    [((
    0.06
    .mixin
    0.06
    Activations Density 0.138%

    No Known Activations