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. 19-RESID-POST-AA
    6. 45103
    Prev
    Next
    INDEX
    Explanations

    occupations and people

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (/^
    -0.07
      	
    -0.07
    $update
    -0.06
     RAW
    -0.06
     Message
    -0.06
    ТО
    -0.06
    _DO
    -0.06
    -enabled
    -0.06
     USB
    -0.06
    ruption
    -0.06
    POSITIVE LOGITS
    *log
    0.07
    .depend
    0.06
     haystack
    0.06
    ();++
    0.06
    asticsearch
    0.06
    �
    0.06
    "><!--
    0.05
    .signal
    0.05
     баг
    0.05
     میل
    0.05
    Activations Density 0.028%

    No Known Activations