Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85175
    Prev
    Next
    INDEX
    Explanations

    moons

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of moons (especially in counts or tables), i.e., where the text refers to the number or listing of “moons.”

    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
     Dt
    -0.06
     소개
    -0.06
    ?url
    -0.06
     buffalo
    -0.06
    vající
    -0.06
     Engines
    -0.06
     fak
    -0.06
    MR
    -0.06
    \FrameworkBundle
    -0.06
    ордин
    -0.06
    POSITIVE LOGITS
    SECRET
    0.07
    ーム
    0.06
     Decomp
    0.06
    Initial
    0.06
     underwater
    0.06
    ))"↵
    0.06
    )arg
    0.06
     پذیر
    0.06
    .Inner
    0.06
     六
    0.06
    Activations Density 0.003%

    No Known Activations