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. 23-RESID-POST-AA
    6. 103985
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QUARE
    -0.07
    Memory
    -0.07
     consenting
    -0.06
    Imagen
    -0.06
     cửa
    -0.06
     itching
    -0.06
    _ori
    -0.06
    	map
    -0.06
     få
    -0.06
    cstring
    -0.06
    POSITIVE LOGITS
     lengthy
    0.07
     Interrupt
    0.07
    .parseFloat
    0.07
     알
    0.06
     inhib
    0.06
     battled
    0.06
    ційної
    0.06
    estinal
    0.06
     питания
    0.06
    ��
    0.06
    Activations Density 0.001%

    No Known Activations