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. 59351
    Prev
    Next
    INDEX
    Explanations

    SUCH

    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
    _floor
    -0.07
    ampton
    -0.07
    Sci
    -0.07
    	im
    -0.06
     director
    -0.06
    І
    -0.06
    college
    -0.06
     iz
    -0.06
     no
    -0.06
     بأ
    -0.06
    POSITIVE LOGITS
     TimeUnit
    0.06
    (normal
    0.06
    雨
    0.06
     přen
    0.06
    perms
    0.06
    bitrary
    0.06
    .hasNext
    0.06
    getProperty
    0.06
    :UIControlEvent
    0.06
    	fire
    0.06
    Activations Density 0.001%

    No Known Activations