© 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. 89832
    Prev
    Next
    INDEX
    Explanations

    ect

    np_max-act · gemini-2.0-flash

    The neuron is essentially detecting subword tokens that belong to proper names or specialized technical terms (i.e. capitalized subwords).

    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
     fondo
    -0.07
    uted
    -0.07
     dou
    -0.07
    ocumented
    -0.07
    ree
    -0.07
    	where
    -0.07
     Inflate
    -0.07
     heavyweight
    -0.07
    Protected
    -0.07
    不好
    -0.06
    POSITIVE LOGITS
    SEL
    0.06
     Ε
    0.06
    ARATION
    0.06
    ίνα
    0.06
     산업
    0.05
    Dlg
    0.05
    digest
    0.05
     Enumerator
    0.05
     oneself
    0.05
    vat
    0.05
    Activations Density 0.141%

    No Known Activations