© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126164
    Prev
    Next
    INDEX
    Explanations

    -old

    np_max-act · gemini-2.0-flash

    details about underage individuals involved in harmful or criminal activities.

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

    This neuron primarily detects age expressions formatted as “[number]-year-old.”

    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
     injury
    -0.06
     приня
    -0.06
     missions
    -0.06
     kural
    -0.06
     Norwich
    -0.06
    -----------↵
    -0.06
    JNIEXPORT
    -0.06
     nominations
    -0.06
     mischief
    -0.06
     parametro
    -0.06
    POSITIVE LOGITS
    -old
    0.08
    shi
    0.07
    bel
    0.07
    -olds
    0.07
    Heading
    0.07
    (`↵
    0.06
     leftover
    0.06
    cid
    0.06
     Troll
    0.06
     Acid
    0.06
    Activations Density 0.012%

    No Known Activations