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. 50520
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    semiconductor memory devices, particularly dynamic random access memory (DRAM) and their components, including capacitors and transistors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    Hook
    -0.07
    تن
    -0.07
    (i
    -0.06
    .item
    -0.06
    takes
    -0.06
    credible
    -0.06
     sabe
    -0.06
    erosis
    -0.06
     screen
    -0.06
    _string
    -0.06
    POSITIVE LOGITS
     IO
    0.06
     někol
    0.06
    -Л
    0.06
     ;;=
    0.06
    /off
    0.06
     QUEUE
    0.06
     fiat
    0.06
    ;:;:;:;:
    0.06
     dev
    0.06
    meter
    0.06
    Activations Density 0.015%

    No Known Activations