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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92012
    Prev
    Next
    INDEX
    Explanations

    generated

    np_max-act · gemini-2.0-flash

    The neuron activates on the “Generated … by javadoc” boilerplate lines in HTML docs (i.e. the auto‐generated Javadoc header comment).

    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
    인지
    -0.07
     Info
    -0.07
    互联网
    -0.07
     observational
    -0.06
     loro
    -0.06
     ramen
    -0.06
     asked
    -0.06
    活
    -0.06
     داشت
    -0.06
    _ISO
    -0.06
    POSITIVE LOGITS
    <Mesh
    0.07
    (parts
    0.06
    Indices
    0.06
    .dequeueReusableCell
    0.06
    _TMP
    0.06
    SelfPermission
    0.06
    Ao
    0.06
    ="{
    0.06
     tamam
    0.06
    eme
    0.06
    Activations Density 0.001%

    No Known Activations