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. 27505
    Prev
    Next
    INDEX
    Explanations

    bg

    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
    command
    -0.07
    diet
    -0.07
     EntityType
    -0.07
    appendChild
    -0.06
    Excel
    -0.06
    	ret
    -0.06
    contract
    -0.06
    _devices
    -0.06
    	method
    -0.06
     dünyanın
    -0.06
    POSITIVE LOGITS
     Bosnia
    0.07
     دل
    0.07
    tür
    0.07
     buffering
    0.07
     SCN
    0.06
     way
    0.06
    рос
    0.06
    .mk
    0.06
     ober
    0.06
    ORY
    0.06
    Activations Density 0.004%

    No Known Activations