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. 85869
    Prev
    Next
    INDEX
    Explanations

    misconceptions

    np_max-act · gemini-2.0-flash

    This neuron activates most strongly on occurrences of the word “misconceptions” (and its subparts) whenever text is labeling or discussing common misunderstandings.

    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
     sign
    -0.07
    comed
    -0.07
     Patty
    -0.07
    _vals
    -0.06
     gesture
    -0.06
    Begin
    -0.06
    -eye
    -0.06
    яття
    -0.06
     relieved
    -0.06
    tax
    -0.06
    POSITIVE LOGITS
     Lip
    0.07
    _GU
    0.07
     جامع
    0.06
    uy�
    0.06
    .Filters
    0.06
    sic
    0.06
    込み
    0.06
    च
    0.06
     Bü
    0.06
    iosper
    0.06
    Activations Density 0.038%

    No Known Activations