© 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. 109687
    Prev
    Next
    INDEX
    Explanations

    zone

    np_max-act · gemini-2.0-flash

    This neuron fires on standalone topic‐style headings or labels (single words or short noun phrases marking a section’s topic).

    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
    ycles
    -0.07
    #ad
    -0.07
     المغ
    -0.07
     barrels
    -0.06
    IGNORE
    -0.06
     ))
    -0.06
    ░
    -0.06
    utral
    -0.06
    ({});↵
    -0.06
     UW
    -0.06
    POSITIVE LOGITS
     Amy
    0.06
    (loader
    0.06
    цію
    0.06
    ريكية
    0.06
    dıktan
    0.06
     milionů
    0.05
     ObjectType
    0.05
    aat
    0.05
    icemail
    0.05
    StyleSheet
    0.05
    Activations Density 0.036%

    No Known Activations