Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99
    Prev
    Next
    INDEX
    Explanations

    Il

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on alphanumeric gene- or protein-style names (e.g. IL-15, SOCS3, TGFβ1, ABCG1, PAPP-A2) – in other words, it finds mentions of specific molecular entities.

    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
    )init
    -0.06
     fus
    -0.06
    Ze
    -0.06
     هج
    -0.06
    )object
    -0.06
     даних
    -0.06
    icopt
    -0.06
    ')?>
    -0.06
    เ
    -0.06
    ocalyptic
    -0.06
    POSITIVE LOGITS
     Mb
    0.07
     Uploaded
    0.06
     sailed
    0.06
     Wall
    0.06
     motivational
    0.06
     seems
    0.06
     dodge
    0.06
     投
    0.06
     findAll
    0.06
     Belediyesi
    0.06
    Activations Density 0.017%

    No Known Activations