© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 36994
    Prev
    Next
    INDEX
    Explanations

    electronics/hardware

    np_max-act · gemini-2.0-flash

    information related to plumbing and heating systems.

    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
     aluminum
    -0.08
    _VAL
    -0.08
    _review
    -0.07
     入
    -0.06
     compound
    -0.06
    avored
    -0.06
     remarks
    -0.06
    .operation
    -0.06
    <(),
    -0.06
    iolet
    -0.06
    POSITIVE LOGITS
    .free
    0.07
    .tie
    0.07
    /lists
    0.06
     ARTICLE
    0.06
    优势
    0.06
    .documentElement
    0.06
     Pfizer
    0.06
     공격
    0.06
    _UI
    0.06
    pecia
    0.06
    Activations Density 0.041%

    No Known Activations