Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130429
    Prev
    Next
    INDEX
    Explanations

    Photography

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “photography” (and its morphological variants).

    oai_token-act-pair · o4-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
     reset
    -0.07
     Client
    -0.07
     исход
    -0.06
     Reset
    -0.06
    Pet
    -0.06
    Get
    -0.06
     cultured
    -0.06
    /rand
    -0.06
     obvious
    -0.06
    Further
    -0.06
    POSITIVE LOGITS
    AMY
    0.09
    ่สามารถ
    0.08
    ρυ
    0.08
     Bakanlığı
    0.08
    RY
    0.08
     maxX
    0.07
    aria
    0.07
    ducation
    0.07
    نة
    0.07
     thờ
    0.07
    Activations Density 0.079%

    No Known Activations