© 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. 56016
    Prev
    Next
    INDEX
    Explanations

    subsequent

    np_max-act · gemini-2.0-flash

    This neuron specifically activates on the word “subsequent,” identifying that exact adverb whenever it appears.

    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
     ripping
    -0.08
    0
    -0.07
     铁
    -0.07
     Гол
    -0.07
     played
    -0.07
     stronger
    -0.07
     RJ
    -0.06
    役
    -0.06
    RX
    -0.06
     fields
    -0.06
    POSITIVE LOGITS
     subsequent
    0.14
     subsequently
    0.11
     ensuing
    0.08
    sequently
    0.08
    sequent
    0.08
     later
    0.08
     outcomes
    0.08
     ensued
    0.08
     násled
    0.07
     이후
    0.07
    Activations Density 0.010%

    No Known Activations