© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 56323
    Prev
    Next
    INDEX
    Explanations

    problem

    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
     engr
    -0.08
     cricket
    -0.07
    十二
    -0.06
     Kir
    -0.06
     hue
    -0.06
    cart
    -0.06
     cart
    -0.06
     Cricket
    -0.06
     bì
    -0.06
    RSS
    -0.06
    POSITIVE LOGITS
     problem
    0.16
     problems
    0.15
     Problem
    0.14
     Problems
    0.11
    problems
    0.11
    problem
    0.10
    Problem
    0.10
     trouble
    0.09
     problème
    0.08
     malfunction
    0.08
    Activations Density 0.050%

    No Known Activations