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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 21920
    Prev
    Next
    INDEX
    Explanations

    Varied, unrelated text snippets

    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
    َا
    -0.07
    荷
    -0.06
    _terminal
    -0.06
    ifr
    -0.06
    �
    -0.06
     alanda
    -0.06
    _VIDEO
    -0.06
     يح
    -0.06
    γού
    -0.06
    說
    -0.06
    POSITIVE LOGITS
     scans
    0.07
     šp
    0.07
    (kwargs
    0.07
    (audio
    0.06
     stared
    0.06
     invisible
    0.06
     Eye
    0.06
    (Matrix
    0.06
     joints
    0.06
    racuse
    0.06
    Activations Density 0.000%

    No Known Activations