© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90755
    Prev
    Next
    INDEX
    Explanations

    ification

    np_max-act · gemini-2.0-flash

    This neuron responds to the word “quantification” (i.e. occurrences of the stem “quant-” plus “-ification”).

    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
    宋
    -0.07
     dose
    -0.06
    Lua
    -0.06
     objs
    -0.06
     پوش
    -0.06
    มา
    -0.06
     celle
    -0.06
    ét
    -0.06
    _slave
    -0.06
     mesma
    -0.06
    POSITIVE LOGITS
    ILog
    0.08
     QtGui
    0.08
     quantify
    0.07
     аж
    0.07
     confirmed
    0.07
    .,↵
    0.07
    )./
    0.07
    bih
    0.07
    ::::::::::::
    0.07
    Unsigned
    0.06
    Activations Density 0.004%

    No Known Activations