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. 83475
    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_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
    	port
    -0.06
     нами
    -0.06
    �
    -0.06
    nThe
    -0.06
     MU
    -0.06
     Rough
    -0.06
    热
    -0.06
    liness
    -0.06
     ringing
    -0.06
     camps
    -0.06
    POSITIVE LOGITS
    642
    0.07
    出品者
    0.07
    _xlim
    0.07
    Ash
    0.07
    ์กร
    0.06
    562
    0.06
    ΗΜΑ
    0.06
    471
    0.06
    府
    0.06
    879
    0.06
    Activations Density 0.000%

    No Known Activations