© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73691
    Prev
    Next
    INDEX
    Explanations

    cities/locations

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on geographic place names in the text.

    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
     гор
    -0.08
     hazard
    -0.07
    _arg
    -0.07
     توضی
    -0.06
     suggest
    -0.06
     })
    ↵
    ↵
    -0.06
     websocket
    -0.06
    -*
    -0.06
    cee
    -0.06
     question
    -0.06
    POSITIVE LOGITS
     strav
    0.06
     Psr
    0.06
    mobx
    0.06
    olson
    0.06
     telev
    0.06
    _frm
    0.06
     ligne
    0.06
    	ep
    0.06
    ning
    0.05
     busty
    0.05
    Activations Density 0.032%

    No Known Activations