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. 122659
    Prev
    Next
    INDEX
    Explanations

    increased/reduced

    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
     Peters
    -0.07
     Theodore
    -0.07
    atı
    -0.07
    either
    -0.07
    \Collections
    -0.07
    _IM
    -0.07
     accession
    -0.06
    contra
    -0.06
     П
    -0.06
    -ons
    -0.06
    POSITIVE LOGITS
    ('');↵
    0.06
     strengthened
    0.06
     GOOD
    0.06
    ])
    ↵
    0.06
     reliable
    0.06
     정확
    0.06
     wang
    0.06
     boosted
    0.06
    ,callback
    0.05
     censorship
    0.05
    Activations Density 0.106%

    No Known Activations