© 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. 15-RESID-POST-AA
    6. 90746
    Prev
    Next
    INDEX
    Explanations

    to

    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
    assador
    -0.06
    ıc
    -0.06
     DEF
    -0.06
    .Customer
    -0.06
     coup
    -0.06
    暮
    -0.06
     referral
    -0.06
     RNA
    -0.06
    _New
    -0.06
    Preferences
    -0.06
    POSITIVE LOGITS
    (sel
    0.07
    іла
    0.07
     solutions
    0.07
    Framework
    0.07
     totally
    0.07
     std
    0.07
     motel
    0.06
    ,:,
    0.06
    �
    0.06
    Eine
    0.06
    Activations Density 0.023%

    No Known Activations