© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 111726
    Prev
    Next
    INDEX
    Explanations

    =

    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
    _running
    -0.07
     According
    -0.06
    Он
    -0.06
    _Destroy
    -0.06
    icht
    -0.06
     Falling
    -0.06
     according
    -0.06
    ].'
    -0.06
    Msg
    -0.06
    echo
    -0.06
    POSITIVE LOGITS
     bamb
    0.08
     النو
    0.07
     unitOfWork
    0.07
     револю
    0.06
    kelig
    0.06
    AGED
    0.06
     polis
    0.06
     SO
    0.06
     Exiting
    0.06
    (mat
    0.06
    Activations Density 0.009%

    No Known Activations