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. 53529
    Prev
    Next
    INDEX
    Explanations

    mistakes

    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_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
    	aux
    -0.09
    QRSTUVWXYZ
    -0.07
     mại
    -0.07
     civilized
    -0.07
    .GridColumn
    -0.07
    _marks
    -0.07
    .getRight
    -0.07
    _multiplier
    -0.07
     Hanna
    -0.07
    illaume
    -0.06
    POSITIVE LOGITS
     verbally
    0.06
     Lib
    0.06
     getResources
    0.06
     aide
    0.06
     optional
    0.06
     zas
    0.06
     ут
    0.06
    sass
    0.06
     sc
    0.05
     času
    0.05
    Activations Density 0.025%

    No Known Activations