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. 31582
    Prev
    Next
    INDEX
    Explanations

    animal extraction/production

    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
    Popup
    -0.07
     details
    -0.07
    Thin
    -0.07
     Đầu
    -0.06
     enzymes
    -0.06
    .skills
    -0.06
    jQuery
    -0.06
    cence
    -0.06
     تن
    -0.06
     landmark
    -0.06
    POSITIVE LOGITS
    ุลาคม
    0.06
    .DateFormat
    0.06
    .OP
    0.06
    .modify
    0.06
    agr
    0.05
    163
    0.05
    467
    0.05
     extremist
    0.05
    527
    0.05
    netinet
    0.05
    Activations Density 0.075%

    No Known Activations