© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95979
    Prev
    Next
    INDEX
    Explanations

    just

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ाह
    -0.06
     Mine
    -0.06
    -Version
    -0.06
     ni
    -0.06
    227
    -0.06
    ателем
    -0.06
    shal
    -0.06
    eld
    -0.06
    状态
    -0.06
    segment
    -0.06
    POSITIVE LOGITS
    Techn
    0.09
    //---------------------------------------------------------------------------↵↵
    0.08
    	RTLI
    0.06
    Iter
    0.06
     अगर
    0.06
     truly
    0.06
     nếu
    0.06
    ناء
    0.06
    (express
    0.06
     Humans
    0.06
    Activations Density 0.005%

    No Known Activations