Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 128898
    Prev
    Next
    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash

    text related to data loading and processing in programming contexts, particularly in the use of pipelines and model initialization.

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

    The neuron strongly activates on the Swedish infinitive marker “att.”

    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
     circa
    -0.07
    _items
    -0.07
     پل
    -0.07
     ל
    -0.07
     JE
    -0.07
    =list
    -0.06
     Taj
    -0.06
     Conte
    -0.06
     stress
    -0.06
     ab
    -0.06
    POSITIVE LOGITS
    381
    0.06
     shortly
    0.06
     calloc
    0.06
    下来
    0.06
    riger
    0.06
    ++)↵
    0.06
     Provides
    0.06
    	volatile
    0.06
     Çok
    0.06
     ZeroConstructor
    0.06
    Activations Density 0.038%

    No Known Activations