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. 11-RESID-POST-AA
    6. 123612
    Prev
    Next
    INDEX
    Explanations

    comma

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contracts
    -0.08
     symmetry
    -0.07
    	control
    -0.07
     ions
    -0.07
    (unique
    -0.07
    _vector
    -0.06
     go
    -0.06
     اهمیت
    -0.06
    temperature
    -0.06
    ibble
    -0.06
    POSITIVE LOGITS
    @m
    0.07
     후보
    0.06
     overseeing
    0.06
     (*)(
    0.06
    uyện
    0.06
     governing
    0.06
    اكم
    0.06
     famil
    0.06
    benhavn
    0.06
    ylland
    0.06
    Activations Density 0.013%

    No Known Activations