Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10453
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    整
    -0.07
    узы
    -0.07
    elenium
    -0.06
     Selenium
    -0.06
     goto
    -0.06
    掉
    -0.06
     Behind
    -0.06
     Chef
    -0.06
            ↵        ↵        ↵
    -0.06
     aftermath
    -0.06
    POSITIVE LOGITS
     rte
    0.07
    (js
    0.06
    ,void
    0.06
     spanish
    0.06
    halt
    0.06
    _foot
    0.06
    	wc
    0.06
     hydraulic
    0.06
    masına
    0.06
    	l
    0.06
    Activations Density 3.127%

    No Known Activations