© 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. 11-RESID-POST-AA
    11. 12997
    Prev
    Next
    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of the verb “get” (and its present‐participle form “getting”) in the text.

    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
    46
    -0.08
    11
    -0.08
    23
    -0.08
    18
    -0.08
    15
    -0.08
    118
    -0.07
    22
    -0.07
    436
    -0.07
    45
    -0.06
     VI
    -0.06
    POSITIVE LOGITS
     get
    0.19
     getting
    0.18
     got
    0.16
     gets
    0.16
     Get
    0.13
    Get
    0.13
     Getting
    0.13
    Getting
    0.13
     Got
    0.13
     GOT
    0.12
    Activations Density 0.108%

    No Known Activations