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. 130758
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    technical terminology related to semiconductor manufacturing processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is specialized to spot the pronoun “it.”

    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
    amework
    -0.07
    870
    -0.07
    EW
    -0.07
     albums
    -0.07
     mutlak
    -0.07
    Same
    -0.07
    杨
    -0.06
     Az
    -0.06
    Lo
    -0.06
    371
    -0.06
    POSITIVE LOGITS
     clearing
    0.06
     [])↵
    0.06
     开
    0.06
     clear
    0.06
     experimenting
    0.06
    .Section
    0.06
    пол
    0.06
    Distribution
    0.06
     journalistic
    0.06
    htable
    0.06
    Activations Density 0.061%

    No Known Activations