© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 54614
    Prev
    Next
    INDEX
    Explanations

    suffix "ose"

    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
    ことも
    -0.07
     dubbed
    -0.07
     humano
    -0.07
     EVAL
    -0.07
    Yellow
    -0.06
     alespoň
    -0.06
     beş
    -0.06
    aravel
    -0.06
     Sat
    -0.06
     будет
    -0.06
    POSITIVE LOGITS
    bv
    0.07
    Ipv
    0.06
    newValue
    0.06
     collaborate
    0.06
    .da
    0.06
     bere
    0.06
    .model
    0.06
    (dataSource
    0.06
     proprietor
    0.06
    mq
    0.06
    Activations Density 0.005%

    No Known Activations