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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30180
    Prev
    Next
    INDEX
    Explanations

    fictional stories

    np_max-act · gemini-2.0-flash

    This neuron detects language describing the process of reversing a transformation—verbs and related nouns about shrinking back down to normal size.

    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
     Firebase
    -0.06
    salary
    -0.06
     Borders
    -0.06
     adicion
    -0.06
     Mosque
    -0.06
     STYLE
    -0.06
    ondon
    -0.06
    gili
    -0.06
     organis
    -0.06
    革命
    -0.06
    POSITIVE LOGITS
    .schema
    0.07
    ierarchy
    0.07
    assertSame
    0.06
    /cc
    0.06
     -->↵
    0.06
     ipairs
    0.06
    Editor
    0.06
    	explicit
    0.06
    .erb
    0.06
     weakening
    0.06
    Activations Density 0.053%

    No Known Activations