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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57698
    Prev
    Next
    INDEX
    Explanations

    sports news articles

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting author‐bylines and related metadata—proper names, media outlet and URL/domain tokens.

    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
     yaml
    -0.07
     evacuated
    -0.07
     अर
    -0.06
     estimator
    -0.06
    ality
    -0.06
    .ali
    -0.06
    .swt
    -0.06
    вид
    -0.06
    Ford
    -0.06
     ///
    -0.06
    POSITIVE LOGITS
    クラブ
    0.07
     filles
    0.06
    classified
    0.06
    ักษณ
    0.06
     thức
    0.06
     Kai
    0.06
     giác
    0.06
     Server
    0.06
     supremacist
    0.06
    雑
    0.06
    Activations Density 0.052%

    No Known Activations