© 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. 3-RESID-POST-AA
    6. 94166
    Prev
    Next
    INDEX
    Explanations

    for

    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
     mutlak
    -0.07
    olen
    -0.06
     seri
    -0.06
    armacy
    -0.06
     pe
    -0.06
     слиз
    -0.06
    .ph
    -0.06
     incentiv
    -0.06
     setOpen
    -0.06
     uğ
    -0.06
    POSITIVE LOGITS
    (span
    0.07
     comrades
    0.07
    ------↵
    0.06
    форт
    0.06
     ♥
    0.06
    谢
    0.06
    	for
    0.06
     ملت
    0.06
    _DECREF
    0.06
    _main
    0.06
    Activations Density 0.026%

    No Known Activations