© 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. 27-RESID-POST-AA
    11. 110402
    Prev
    Next
    INDEX
    Explanations

    ;

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     energy
    -0.07
    zos
    -0.07
    ayout
    -0.07
    	client
    -0.06
    材
    -0.06
    Settings
    -0.06
    =df
    -0.06
     Commands
    -0.06
     Room
    -0.06
    	current
    -0.06
    POSITIVE LOGITS
     PŘ
    0.06
    _beh
    0.06
    amble
    0.06
    bler
    0.06
    Nous
    0.06
    ันธ
    0.06
     climb
    0.06
     대표
    0.06
    celed
    0.06
    ledik
    0.06
    Activations Density 0.002%

    No Known Activations