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. 7-RESID-POST-AA
    6. 111526
    Prev
    Next
    INDEX
    Explanations

    animals

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refill
    -0.07
     Flat
    -0.07
     Cox
    -0.06
    (part
    -0.06
     language
    -0.06
    .clock
    -0.06
    stva
    -0.06
     monot
    -0.06
    336
    -0.06
     골
    -0.06
    POSITIVE LOGITS
    acağını
    0.07
    driver
    0.07
    VENTORY
    0.06
    endpoint
    0.06
     IPCC
    0.06
    ानव
    0.06
    ��
    0.06
    .OrdinalIgnoreCase
    0.06
    GTK
    0.06
    vincia
    0.06
    Activations Density 0.122%

    No Known Activations