© 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. 30178
    Prev
    Next
    INDEX
    Explanations

    hair salons / style

    np_max-act · gemini-2.0-flash

    business names related to hairdressing and hairstyling.

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

    The neuron activates on mentions of hair‐service business terms—especially “hair,” “salon,” “stylist,” and related service words.

    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
     حل
    -0.07
    出
    -0.07
    _dataframe
    -0.07
     slipping
    -0.06
    	matrix
    -0.06
    _runs
    -0.06
    황
    -0.06
    HOOK
    -0.06
    \uff
    -0.06
     AQ
    -0.06
    POSITIVE LOGITS
    urrenc
    0.07
    osi
    0.06
    :C
    0.06
    February
    0.06
    riendly
    0.06
    ịp
    0.06
     miktar
    0.06
    ATFORM
    0.06
    igmat
    0.06
    íně
    0.06
    Activations Density 0.012%

    No Known Activations