© 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. 6962
    Prev
    Next
    INDEX
    Explanations

    perfect tense auxiliary verbs

    np_max-act · gemini-2.0-flash

    information about organizational planning and events related to community engagement.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on verbs and auxiliaries that signal ongoing activity or planned actions (e.g. has/been working, planning, started).

    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
     western
    -0.07
     interpreting
    -0.06
    ell
    -0.06
     exon
    -0.06
    ITERAL
    -0.06
     Criterion
    -0.06
    -values
    -0.06
     sunk
    -0.06
    its
    -0.06
     liquids
    -0.06
    POSITIVE LOGITS
    	d
    0.06
     muže
    0.06
    ObjectContext
    0.06
     seamlessly
    0.06
     �
    0.06
    leri
    0.06
     setContent
    0.06
    θενής
    0.06
    ->[
    0.06
    (nr
    0.06
    Activations Density 0.052%

    No Known Activations