© 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. 88908
    Prev
    Next
    INDEX
    Explanations

    academic publications and articles

    np_max-act · gemini-2.0-flash

    The neuron detects reporting verbs that announce academic or professional milestones—e.g. “has,” “was,” “named,” “received,” “published,” “will be”—marking formal achievement or appointment statements.

    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
     Sav
    -0.07
     아닌
    -0.06
     formation
    -0.06
     вид
    -0.06
     Sant
    -0.06
    кувати
    -0.06
     behaved
    -0.06
    備
    -0.06
    _JOIN
    -0.06
     Fargo
    -0.06
    POSITIVE LOGITS
     Composer
    0.07
    /wp
    0.07
    ۲۶
    0.06
     کلاس
    0.06
     bure
    0.06
    >Lorem
    0.06
    :";↵
    0.06
    •↵↵
    0.06
     bere
    0.06
    bars
    0.06
    Activations Density 0.033%

    No Known Activations