© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55987
    Prev
    Next
    INDEX
    Explanations

    engineering

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on specialized engineering compound nouns and technical process names (e.g. “wafer level packaging,” “twist drills”).

    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
     organized
    -0.07
    .SIG
    -0.07
     }//
    -0.06
     раск
    -0.06
     Dann
    -0.06
     dét
    -0.06
    ())){↵
    -0.06
    	ok
    -0.06
    .way
    -0.06
     phạt
    -0.06
    POSITIVE LOGITS
                            
    0.07
    _RENDER
    0.07
    Apollo
    0.07
     Obesity
    0.07
    ↵
    ↵
    ↵
    0.07
     Mosque
    0.06
    ESH
    0.06
    geries
    0.06
    antas
    0.06
     ^{}
    0.06
    Activations Density 0.103%

    No Known Activations