© 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. 14084
    Prev
    Next
    INDEX
    Explanations

    separation processes

    np_max-act · gemini-2.0-flash

    The neuron flags language describing chromatographic purification steps—especially mentions of passing a mixture through a packed column with a solid adsorbent.

    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
    usr
    -0.06
    	effect
    -0.06
    鉄道
    -0.06
    MR
    -0.06
     när
    -0.06
    Consult
    -0.06
    /cc
    -0.06
    _Server
    -0.06
     rift
    -0.06
    _floor
    -0.06
    POSITIVE LOGITS
     wore
    0.06
     ""));↵
    0.06
    (age
    0.06
    ็จ
    0.06
    /Delete
    0.06
     PreparedStatement
    0.06
     magnitude
    0.06
    ]==
    0.06
    .sqlite
    0.06
     communic
    0.06
    Activations Density 0.029%

    No Known Activations