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. 21096
    Prev
    Next
    INDEX
    Explanations

    in

    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
    AINS
    -0.07
     homepage
    -0.06
    альної
    -0.06
     preacher
    -0.06
    orch
    -0.06
    explode
    -0.06
    альні
    -0.06
    	option
    -0.06
    gear
    -0.06
    ainted
    -0.06
    POSITIVE LOGITS
    มข
    0.07
     Země
    0.07
     Ethan
    0.07
     Sext
    0.06
    (argv
    0.06
     gql
    0.06
    tokens
    0.06
    	en
    0.06
     SimpleDateFormat
    0.06
    (tr
    0.06
    Activations Density 0.026%

    No Known Activations