© 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. 19-RESID-POST-AA
    11. 91688
    Prev
    Next
    INDEX
    Explanations

    protection

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shifts
    -0.07
     arcs
    -0.07
    ('//
    -0.06
    Code
    -0.06
     caves
    -0.06
     passes
    -0.06
     deleted
    -0.06
     booming
    -0.06
    	scanf
    -0.06
    ZA
    -0.06
    POSITIVE LOGITS
     protection
    0.08
    _ef
    0.07
     cushion
    0.07
    寶
    0.07
    ков
    0.07
     bolster
    0.07
    flt
    0.07
    asure
    0.07
    eselect
    0.07
    parency
    0.06
    Activations Density 0.017%

    No Known Activations