© 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. 46583
    Prev
    Next
    INDEX
    Explanations

    while

    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
    uce
    -0.06
    .setTime
    -0.06
    _Copy
    -0.06
    	A
    -0.06
     trailing
    -0.06
    romise
    -0.06
     空
    -0.06
    ,E
    -0.05
     constantly
    -0.05
     Couple
    -0.05
    POSITIVE LOGITS
     wildly
    0.07
    ₃
    0.07
    Https
    0.07
    (".")
    0.07
     accompl
    0.07
     ['$
    0.07
     نوش
    0.07
     Gover
    0.07
    -Series
    0.06
    inea
    0.06
    Activations Density 0.333%

    No Known Activations