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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 28000
    Prev
    Next
    INDEX
    Explanations

    legislatures and governments

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SelectionMode
    -0.07
     YE
    -0.07
    iscing
    -0.07
    FD
    -0.06
    ();
    
    ↵
    -0.06
    '))
    ↵
    -0.06
     BCM
    -0.06
    (next
    -0.06
    ,
    ↵
    ↵
    -0.06
     Sim
    -0.06
    POSITIVE LOGITS
     chlap
    0.07
     Baltimore
    0.07
     unleashed
    0.07
     Nintendo
    0.06
     Saints
    0.06
    午
    0.06
     art
    0.06
     Budapest
    0.06
     찾
    0.06
     примен
    0.06
    Activations Density 0.010%

    No Known Activations