© 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. 29591
    Prev
    Next
    INDEX
    Explanations

    that

    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
     способом
    -0.07
     Brom
    -0.07
    227
    -0.06
     oxy
    -0.06
    11
    -0.06
    شناسی
    -0.06
    ();↵↵↵
    -0.06
     основных
    -0.06
     bean
    -0.06
    埃
    -0.06
    POSITIVE LOGITS
     that
    0.26
    that
    0.20
     That
    0.19
     THAT
    0.19
    That
    0.16
    	that
    0.14
    -that
    0.13
     dat
    0.13
    (that
    0.11
    "That
    0.11
    Activations Density 0.659%

    No Known Activations