© 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. 124906
    Prev
    Next
    INDEX
    Explanations

    plan

    np_max-act · gemini-2.0-flash

    The neuron spikes on occurrences of “plan” or “plans,” i.e. verbs expressing future intent.

    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
    یط
    -0.08
     SolidColorBrush
    -0.07
     synthesis
    -0.07
     theta
    -0.07
    ashboard
    -0.07
    Roles
    -0.06
     Identity
    -0.06
    BUTTON
    -0.06
     Blood
    -0.06
     becomes
    -0.06
    POSITIVE LOGITS
     planning
    0.09
     planned
    0.09
     plans
    0.08
     intended
    0.07
     plan
    0.07
     meslek
    0.07
    办理
    0.06
     Restart
    0.06
     LIMIT
    0.06
    申请
    0.06
    Activations Density 0.014%

    No Known Activations