© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29724
    Prev
    Next
    INDEX
    Explanations

    inner

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of interior or internal parts (e.g., “interior,” “internally,” “inside”).

    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
     find
    -0.07
    	File
    -0.07
     мест
    -0.06
     Identification
    -0.06
    plates
    -0.06
     tus
    -0.06
    .Delete
    -0.06
    >e
    -0.06
     zemí
    -0.06
     samples
    -0.06
    POSITIVE LOGITS
     inner
    0.08
     internal
    0.07
    .djangoproject
    0.07
    BackingField
    0.07
     ($)
    0.06
     çarp
    0.06
    否
    0.06
    raham
    0.06
    内
    0.06
     inside
    0.06
    Activations Density 0.056%

    No Known Activations