© 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. 11-RESID-POST-AA
    11. 57285
    Prev
    Next
    INDEX
    Explanations

    Repetitions (reps)

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens and thus does not detect any particular feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bruary
    -0.06
    usion
    -0.06
     "\\"
    -0.06
    Kal
    -0.06
    patients
    -0.06
    antasy
    -0.06
     tests
    -0.06
    method
    -0.06
    methods
    -0.06
     criticizing
    -0.06
    POSITIVE LOGITS
     rasp
    0.07
     перепис
    0.06
     incest
    0.06
     communion
    0.06
    áp
    0.06
     Spiritual
    0.06
    UITableViewCell
    0.06
     Yii
    0.06
    ồi
    0.06
     Sampling
    0.06
    Activations Density 0.003%

    No Known Activations