© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 60209
    Prev
    Next
    INDEX
    Explanations

    Etymology

    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
    	dir
    -0.07
    [model
    -0.06
     autos
    -0.06
    İn
    -0.06
    	Input
    -0.06
     UnityEditor
    -0.06
     �
    -0.06
     antlr
    -0.06
    Він
    -0.06
    ーク
    -0.06
    POSITIVE LOGITS
     individual
    0.06
    _gene
    0.06
     vol
    0.06
    WH
    0.06
    variants
    0.06
     Ser
    0.06
    quan
    0.06
    -band
    0.06
    icap
    0.06
     Cr
    0.06
    Activations Density 0.107%

    No Known Activations