© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9388
    Prev
    Next
    INDEX
    Explanations

    plans and arrangements

    np_max-act · gemini-2.0-flash

    The neuron fires on words that signal future or ongoing actions and plans (e.g. “will,” “are being,” “ways,” “consider,” “possible”).

    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
     perverse
    -0.06
    normalize
    -0.06
    орм
    -0.06
    ์เน
    -0.06
     Take
    -0.06
    尾
    -0.06
    Versions
    -0.06
     underway
    -0.05
    west
    -0.05
     uống
    -0.05
    POSITIVE LOGITS
     freq
    0.07
     Democr
    0.07
    filtro
    0.07
    .pos
    0.07
     truncate
    0.07
     Europa
    0.07
    AVA
    0.07
     preamble
    0.07
     ود
    0.07
     Cumhuriyeti
    0.07
    Activations Density 0.069%

    No Known Activations