© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 92771
    Prev
    Next
    INDEX
    Explanations

    deception

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _regs
    -0.07
     filho
    -0.07
    _LD
    -0.06
     snad
    -0.06
     }
↵
↵
    -0.06
     ','
    -0.06
    .same
    -0.06
    _bank
    -0.06
     wildfires
    -0.06
    -framework
    -0.06
    POSITIVE LOGITS
     deceived
    0.10
     deception
    0.09
     deceptive
    0.08
     deceive
    0.08
     deceit
    0.06
     dece
    0.06
    [sub
    0.06
    ookie
    0.06
    psilon
    0.06
     reasoning
    0.06
    Activations Density 0.009%

    No Known Activations