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. 3-RESID-POST-AA
    6. 94374
    Prev
    Next
    INDEX
    Explanations

    led

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     张
    -0.07
     rue
    -0.06
     уник
    -0.06
    889
    -0.06
     Orioles
    -0.06
    .Safe
    -0.06
    _changes
    -0.06
     roadside
    -0.06
    ้า
    -0.06
    /simple
    -0.06
    POSITIVE LOGITS
     led
    0.19
    -led
    0.09
     prompting
    0.08
    τερ
    0.07
     Led
    0.07
    Led
    0.07
    英語
    0.07
     writes
    0.07
     gehört
    0.06
    gd
    0.06
    Activations Density 0.007%

    No Known Activations