© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13596
    Prev
    Next
    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are JavaScript/JSON object property names (i.e. keys in data/config literals).

    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
     Sponge
    -0.07
    hf
    -0.07
     sponge
    -0.06
    洞
    -0.06
     华
    -0.06
    GraphQL
    -0.06
     frameworks
    -0.06
     sty
    -0.06
     ylim
    -0.06
     scient
    -0.06
    POSITIVE LOGITS
    ्डल
    0.07
     SENT
    0.06
     truly
    0.06
     possível
    0.06
     threaded
    0.06
    ίλ
    0.06
     earthly
    0.06
    niest
    0.05
    َّ
    0.05
    she
    0.05
    Activations Density 0.096%

    No Known Activations