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

    Neuronpedia

    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. 126926
    Prev
    Next
    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash

    The neuron is detecting the placeholder token “NAME_1” (i.e. an entity‐name placeholder).

    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
     тобто
    -0.07
     yö
    -0.07
    _BR
    -0.06
     CZ
    -0.06
    .operation
    -0.06
    .LatLng
    -0.06
    Africa
    -0.06
     kale
    -0.06
    feld
    -0.06
    Ty
    -0.06
    POSITIVE LOGITS
    िजल
    0.07
    *:
    0.06
    uintptr
    0.06
     stark
    0.06
     процессе
    0.06
    孩
    0.06
     TWO
    0.06
    (master
    0.06
    .GetBytes
    0.06
    AxisAlignment
    0.06
    Activations Density 0.004%

    No Known Activations