Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 103915
    Prev
    Next
    INDEX
    Explanations

    red carpet events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleasant
    -0.07
     Third
    -0.07
     THIRD
    -0.07
     Treatment
    -0.07
    î
    -0.06
    Treatment
    -0.06
    анов
    -0.06
     Pres
    -0.06
    ui
    -0.06
    ede
    -0.06
    POSITIVE LOGITS
     olmam
    0.07
    			    
    0.06
    StateToProps
    0.06
    			     
    0.06
    …..
    0.06
     başlamış
    0.06
    ered
    0.06
        	 
    0.06
    μείο
    0.06
    ........
    0.06
    Activations Density 0.025%

    No Known Activations