© 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. 7-RESID-POST-AA
    11. 21629
    Prev
    Next
    INDEX
    Explanations

    Verb forms ending in -ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	cuda
    -0.07
     AssemblyCompany
    -0.07
    'ét
    -0.07
     kunne
    -0.06
     dynam
    -0.06
     basePath
    -0.06
     serviceName
    -0.06
     Genuine
    -0.06
    ,std
    -0.06
     inert
    -0.06
    POSITIVE LOGITS
     surprising
    0.08
     confusing
    0.08
     damaging
    0.08
    INGER
    0.07
     entertaining
    0.07
     encouraging
    0.07
     frustrating
    0.07
     engaging
    0.07
     summons
    0.07
     Brigham
    0.07
    Activations Density 0.073%

    No Known Activations