© 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. 42907
    Prev
    Next
    INDEX
    Explanations

    writer profiles

    np_max-act · gemini-2.0-flash

    The neuron activates on staff‐byline or author‐bio lines (journalist credits and affiliations).

    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
    conciliation
    -0.07
    .render
    -0.07
     konkrét
    -0.06
     Exploration
    -0.06
    -vers
    -0.06
     signs
    -0.06
     yık
    -0.06
    th
    -0.06
     palindrome
    -0.06
    عار
    -0.06
    POSITIVE LOGITS
    	W
    0.07
     bigger
    0.07
    orelease
    0.06
     smaller
    0.06
     cestu
    0.06
    _CLR
    0.06
     SHA
    0.06
     innoc
    0.06
     Organizer
    0.06
    /results
    0.06
    Activations Density 0.008%

    No Known Activations