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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 30064
    Prev
    Next
    INDEX
    Explanations

    Code/programming syntax

    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
     markdown
    -0.06
    cla
    -0.06
    *out
    -0.06
     Bias
    -0.06
    cus
    -0.06
    ination
    -0.06
     arise
    -0.06
     rumours
    -0.06
     freed
    -0.06
     power
    -0.06
    POSITIVE LOGITS
    	 	
    0.07
    .Ge
    0.06
    [attr
    0.06
     executions
    0.06
     progressDialog
    0.06
    (Float
    0.06
     operative
    0.06
    nox
    0.06
     BIT
    0.06
    Blocking
    0.06
    Activations Density 0.181%

    No Known Activations