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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 52649
    Prev
    Next
    INDEX
    Explanations

    pathway

    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
     رود
    -0.07
    .easing
    -0.07
     jednot
    -0.07
     kinetics
    -0.06
     уда
    -0.06
     जम
    -0.06
     outdoors
    -0.06
    EDGE
    -0.06
    炉
    -0.06
     omas
    -0.06
    POSITIVE LOGITS
    xAF
    0.06
    	perror
    0.06
    $url
    0.06
    	common
    0.06
    '=>
    0.06
    OOSE
    0.06
    			    
    0.06
     unaffected
    0.06
    crafted
    0.06
    파
    0.06
    Activations Density 0.000%

    No Known Activations