© 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
    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. 30541
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the phrase “going to” as a future‐tense auxiliary.

    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
     adher
    -0.08
    REFIX
    -0.07
     adherence
    -0.06
    ,而
    -0.06
    Objects
    -0.06
    Hard
    -0.06
    	hs
    -0.06
    lz
    -0.06
    芙
    -0.06
    เช
    -0.06
    POSITIVE LOGITS
     gonna
    0.13
    going
    0.09
     going
    0.08
     will
    0.07
    gon
    0.07
     Mog
    0.07
    pon
    0.07
    igator
    0.07
    gua
    0.07
     Gon
    0.07
    Activations Density 0.018%

    No Known Activations