© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 66368
    Prev
    Next
    INDEX
    Explanations

    essay structure

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doanh
    -0.07
    coc
    -0.07
    !!
    -0.07
    Preview
    -0.06
     goo
    -0.06
     iki
    -0.06
     dospěl
    -0.06
    	results
    -0.06
     мин
    -0.06
    avorites
    -0.06
    POSITIVE LOGITS
     Ceramic
    0.07
    _points
    0.07
    attach
    0.07
    ｍ
    0.07
     Tick
    0.06
    应该
    0.06
    _tele
    0.06
    �
    0.06
    _pr
    0.06
    redi
    0.06
    Activations Density 0.033%

    No Known Activations