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. 8707
    Prev
    Next
    INDEX
    Explanations

    file types and programming

    np_max-act · gemini-2.0-flash

    This neuron fires on PDFBox API identifiers prefixed with “PD,” i.e. class and type names from the PDFBox library.

    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
    _TYPED
    -0.08
    �
    -0.07
     utterly
    -0.07
    iyor
    -0.07
     African
    -0.06
     Mechanics
    -0.06
     î
    -0.06
    	properties
    -0.06
    Deleting
    -0.06
    приклад
    -0.06
    POSITIVE LOGITS
    ‘s
    0.06
     meanings
    0.06
    已
    0.06
    Operating
    0.06
    ~↵↵
    0.06
    (".
    0.06
     रखन
    0.06
     xlink
    0.06
    arranty
    0.06
     Đảng
    0.06
    Activations Density 0.035%

    No Known Activations