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. 30733
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
     zur
    -0.07
     прим
    -0.07
    ">&#
    -0.07
    _seqs
    -0.06
     değiştir
    -0.06
     сказал
    -0.06
     区
    -0.06
    یس
    -0.06
     ;;^
    -0.06
    剩
    -0.06
    POSITIVE LOGITS
     Container
    0.07
     firm
    0.07
     Turbo
    0.07
    Field
    0.07
    (commit
    0.07
     sorts
    0.07
     taco
    0.07
     arrival
    0.07
    	 
    ↵
    0.07
     Nicole
    0.07
    Activations Density 0.000%

    No Known Activations