© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 57881
    Prev
    Next
    INDEX
    Explanations

    noqa

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     telling
    -0.06
     pois
    -0.06
    	diff
    -0.06
     forks
    -0.06
    	trans
    -0.06
     service
    -0.06
     Υ
    -0.06
     '/../
    -0.06
     ".",
    -0.06
    开放
    -0.05
    POSITIVE LOGITS
    .getSelectionModel
    0.07
     �
    0.06
    づ
    0.06
    .ItemStack
    0.06
    defgroup
    0.06
    _UTF
    0.06
    ходим
    0.06
     successors
    0.06
     Orwell
    0.06
     حرفه
    0.06
    Activations Density 0.002%

    No Known Activations