© 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
    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. 52414
    Prev
    Next
    INDEX
    Explanations

    Code/equations/special characters

    np_max-act · gemini-2.0-flash

    It detects technical chemical/chemical‑industry terminology—especially long chemical compound names and words about synthesis/production.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
     doğ
    -0.06
    .ib
    -0.06
    ـــ
    -0.06
    删除
    -0.06
     현재
    -0.05
     слыш
    -0.05
    _NOTICE
    -0.05
     показ
    -0.05
    ıt
    -0.05
     wp
    -0.05
    POSITIVE LOGITS
     підс
    0.07
     �
    0.06
     امن
    0.06
     impro
    0.06
     →↵↵
    0.06
    TestingModule
    0.06
     Sink
    0.06
    ะแนน
    0.06
    	on
    0.06
     l
    0.06
    Activations Density 14.239%

    No Known Activations