© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 124781
    Prev
    Next
    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash

    This neuron responds to terms related to Time Machine–style backups and versioned snapshots (e.g. images, saves, hourly/daily/weekly backups, history, incremental).

    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
    eff
    -0.07
     misplaced
    -0.06
    posite
    -0.06
     Yamaha
    -0.06
     Strip
    -0.06
     Slovenia
    -0.06
     Spiral
    -0.06
     prefixes
    -0.06
    Streamer
    -0.06
    iydi
    -0.05
    POSITIVE LOGITS
     commun
    0.07
     RootState
    0.07
     "(\<
    0.07
     lĩnh
    0.07
    학년
    0.06
    .wallet
    0.06
    ामल
    0.06
     commodities
    0.06
    nav
    0.06
    อาช
    0.06
    Activations Density 0.013%

    No Known Activations