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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 123376
    Prev
    Next
    INDEX
    Explanations

    controversial

    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
    онь
    -0.07
    Scan
    -0.06
     ミ
    -0.06
    meldung
    -0.06
     látky
    -0.06
    chein
    -0.06
     имеют
    -0.06
     elde
    -0.06
     어려
    -0.06
     anecdotes
    -0.06
    POSITIVE LOGITS
     controversial
    0.35
     contentious
    0.13
     disputed
    0.09
     divisive
    0.09
     sensitive
    0.07
     controvers
    0.07
     lon
    0.07
     ]);↵↵
    0.07
    })"↵
    0.07
     unusual
    0.07
    Activations Density 0.002%

    No Known Activations