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. 53457
    Prev
    Next
    INDEX
    Explanations

    single

    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
     improvement
    -0.06
    mom
    -0.06
     product
    -0.06
     kterém
    -0.06
    Charge
    -0.06
    CreateDate
    -0.06
     organic
    -0.06
    ates
    -0.06
    농
    -0.06
    amentals
    -0.06
    POSITIVE LOGITS
    rett
    0.07
    []){↵
    0.07
    速
    0.07
    labs
    0.06
     наб
    0.06
    /manual
    0.06
    稳
    0.06
     Medic
    0.06
    فو
    0.06
    /token
    0.06
    Activations Density 0.249%

    No Known Activations