© 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 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. 56483
    Prev
    Next
    INDEX
    Explanations

    Politics and financial corruption

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of organizations, companies, industries, or other institutional entities (proper nouns referring to groups).

    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
    	from
    -0.06
     Nose
    -0.06
     حم
    -0.06
    reshape
    -0.06
     Addiction
    -0.06
    recv
    -0.06
     upfront
    -0.06
    -carousel
    -0.06
     chapters
    -0.06
     Determine
    -0.06
    POSITIVE LOGITS
     expenditures
    0.07
     Correspond
    0.07
    !*
    0.07
    りの
    0.07
     Breitbart
    0.06
    pective
    0.06
     II
    0.06
    mate
    0.06
    블
    0.06
    ordial
    0.06
    Activations Density 0.012%

    No Known Activations