© 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
    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. 8969
    Prev
    Next
    INDEX
    Explanations

    ole

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the words “dipole” or “dipolar,” i.e. it detects mention of dipole-related terminology.

    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
    (flags
    -0.07
    WithString
    -0.07
    대행
    -0.06
     Sheikh
    -0.06
     Dan
    -0.06
     Она
    -0.06
    Sport
    -0.06
    .SharedPreferences
    -0.06
     tarihli
    -0.06
     whispers
    -0.06
    POSITIVE LOGITS
    magic
    0.08
     mij
    0.07
    의
    0.07
    それは
    0.07
    xFC
    0.06
    utura
    0.06
     φω
    0.06
    \System
    0.06
    'user
    0.06
     ΔE
    0.06
    Activations Density 0.002%

    No Known Activations