© 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. 726
    Prev
    Next
    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash

    narrative elements related to personal experiences and emotional turmoil.

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

    The neuron flags language that denotes a comparison being made between things.

    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
    anning
    -0.07
    زن
    -0.06
    っぱい
    -0.06
     tato
    -0.06
    references
    -0.06
    -score
    -0.06
    ěl
    -0.06
    сього
    -0.06
    	em
    -0.06
    inho
    -0.06
    POSITIVE LOGITS
     infinitely
    0.06
     вст
    0.06
     coraz
    0.06
     açısından
    0.06
    اگر
    0.06
     intern
    0.06
    .getString
    0.06
    _package
    0.06
    ์ฟ
    0.06
    ，就
    0.06
    Activations Density 0.170%

    No Known Activations