© 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. 129789
    Prev
    Next
    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “following” when it’s used to introduce a list or examples.

    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
    опрос
    -0.07
    udo
    -0.07
     deltaY
    -0.07
    IDO
    -0.07
    Pr
    -0.06
    ife
    -0.06
     Id
    -0.06
    -int
    -0.06
    jd
    -0.06
     ид
    -0.06
    POSITIVE LOGITS
     following
    0.10
    went
    0.07
     follows
    0.07
     fleet
    0.07
     fundraising
    0.07
    [row
    0.06
    ":
↵
    0.06
     Following
    0.06
     koneč
    0.06
     lingu
    0.06
    Activations Density 0.050%

    No Known Activations