© 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 (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 54739
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    <Player
    -0.06
    �
    -0.06
     reprodu
    -0.06
     дозвол
    -0.06
    ющим
    -0.06
     lure
    -0.06
     Aerospace
    -0.06
    とい
    -0.06
     dönüş
    -0.06
     oneself
    -0.06
    POSITIVE LOGITS
    _UN
    0.07
    _THAN
    0.06
     Bomb
    0.06
    /f
    0.06
    زو
    0.06
    	describe
    0.06
    	sb
    0.06
    /init
    0.06
    Recipes
    0.06
    	dst
    0.06
    Activations Density 0.000%

    No Known Activations