© 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. 92155
    Prev
    Next
    INDEX
    Explanations

    preferred

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of patent-style preference markers (e.g. “preferred,” “preferably,” “embodiments,” etc.).

    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
    -ring
    -0.06
     appId
    -0.06
     bugs
    -0.06
    cles
    -0.06
    registry
    -0.06
    řel
    -0.06
     alias
    -0.06
     next
    -0.06
     makeup
    -0.06
    'post
    -0.06
    POSITIVE LOGITS
    †
    0.07
     місцев
    0.07
    VERTISEMENT
    0.07
     ků
    0.07
    想要
    0.07
    �
    0.06
     suited
    0.06
     까
    0.06
    _SC
    0.06
    .partner
    0.06
    Activations Density 0.007%

    No Known Activations