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. 3-RESID-POST-AA
    6. 122469
    Prev
    Next
    INDEX
    Explanations

    Jackson

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ie
    -0.07
     Indianapolis
    -0.07
    -loop
    -0.06
    383
    -0.06
    одатель
    -0.06
     diaper
    -0.06
     metabolism
    -0.06
    �
    -0.06
    	va
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Jackson
    0.38
    Jackson
    0.29
    ackson
    0.17
    ulton
    0.09
     Fulton
    0.08
    .jackson
    0.08
    continent
    0.07
    .ObjectMapper
    0.07
    SON
    0.07
    agement
    0.07
    Activations Density 0.002%

    No Known Activations