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. 84385
    Prev
    Next
    INDEX
    Explanations

    silica

    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
     continuing
    -0.08
    串
    -0.07
    AspNet
    -0.07
     slapped
    -0.07
     Sean
    -0.06
     replace
    -0.06
    未
    -0.06
     captain
    -0.06
     Mission
    -0.06
    ang
    -0.06
    POSITIVE LOGITS
     silica
    0.08
     ciclo
    0.07
     Nico
    0.06
     DHS
    0.06
     acuerdo
    0.06
     libido
    0.06
    optimize
    0.06
    -ac
    0.06
     SimpleDateFormat
    0.06
    ilters
    0.06
    Activations Density 0.003%

    No Known Activations