© 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
    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. 53611
    Prev
    Next
    INDEX
    Explanations

    y

    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
     veřejné
    -0.07
    ています
    -0.06
    營
    -0.06
    Stuff
    -0.06
    	graph
    -0.06
    .wp
    -0.06
     modified
    -0.06
    <t
    -0.06
    nocení
    -0.06
     autre
    -0.06
    POSITIVE LOGITS
     떠
    0.07
     Cities
    0.07
     folded
    0.07
     mentioning
    0.06
     reassuring
    0.06
     overarching
    0.06
    iation
    0.06
    rer
    0.06
    .DOM
    0.06
     Fior
    0.06
    Activations Density 0.005%

    No Known Activations